{"url":"/sota/monocular-depth-estimation-on-nyu-depth-v2","task":{"name":"Monocular Depth Estimation","url":"/task/monocular-depth-estimation","note":null},"dataset":{"name":"NYU-Depth V2","url":"/dataset/nyuv2"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Monocular Depth Estimation** is the task of estimating the depth value (distance relative to the camera) of each pixel given a single (monocular) RGB image. This challenging task is a key prerequisite for determining scene understanding for applications such as 3D scene reconstruction, autonomous driving, and AR. State-of-the-art methods usually fall into one of two categories: designing a complex network that is powerful enough to directly regress the depth map, or splitting the input into bins or windows to reduce computational complexity.  The most popular benchmarks are the KITTI and NYUv2 datasets. Models are typically evaluated using RMSE or absolute relative error. \r\n\r\n<span class=\"description-source\">Source: [Defocus Deblurring Using Dual-Pixel Data ](https://arxiv.org/abs/2005.00305)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["absolute relative error","RMSE","log 10","Delta < 1.25","Delta < 1.25^2","Delta < 1.25^3"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"absolute relative error":"lower","RMSE":"lower","log 10":null,"Delta < 1.25":null,"Delta < 1.25^2":null,"Delta < 1.25^3":null}},"counts":{"rows":85,"rows_with_code":71,"rows_with_paper_page":85,"rows_dated":85,"rows_using_additional_data":22},"rows":[{"rank_in_archive_order":1,"model":"HybridDepth","metrics":{"Delta < 1.25":"0.988","Delta < 1.25^2":"1.000","Delta < 1.25^3":"1.000","RMSE":"0.128","absolute relative error":"0.026"},"uses_additional_data":false,"paper_date":"2024-07-26","paper":"/paper/hybriddepth-robust-depth-fusion-for-mobile-ar","paper_url":"https://arxiv.org/abs/2407.18443v3","paper_title":"HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image Priors","code":"https://github.com/cake-lab/hybriddepth","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":2,"model":"Distill Any Depth","metrics":{"Delta < 1.25":"0.981","absolute relative error":"0.043"},"uses_additional_data":false,"paper_date":"2025-02-26","paper":"/paper/distill-any-depth-distillation-creates-a","paper_url":"https://arxiv.org/abs/2502.19204v2","paper_title":"Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator","code":"https://github.com/Westlake-AGI-Lab/Distill-Any-Depth","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"UniK3D (FT, metric)","metrics":{"Delta < 1.25":"0.989","Delta < 1.25^2":"0.998","Delta < 1.25^3":"1.000","RMSE":"0.173","absolute relative error":"0.044","log 10":"0.019"},"uses_additional_data":false,"paper_date":"2025-03-20","paper":"/paper/unik3d-universal-camera-monocular-3d","paper_url":"https://arxiv.org/abs/2503.16591v1","paper_title":"UniK3D: Universal Camera Monocular 3D Estimation","code":"https://github.com/lpiccinelli-eth/UniK3D","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"UniDepthV2 (FT, metric)","metrics":{"Delta < 1.25":"0.988","Delta < 1.25^2":"0.998","Delta < 1.25^3":"1.000","RMSE":"0.180","absolute relative error":"0.046","log 10":"0.020"},"uses_additional_data":true,"paper_date":"2025-02-27","paper":"/paper/unidepthv2-universal-monocular-metric-depth","paper_url":"https://arxiv.org/abs/2502.20110v1","paper_title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","code":"https://github.com/lpiccinelli-eth/unidepth","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":5,"model":"PrimeDepth + Depth Anything","metrics":{"Delta < 1.25":"0.977","absolute relative error":"0.046"},"uses_additional_data":false,"paper_date":"2024-09-13","paper":"/paper/primedepth-efficient-monocular-depth","paper_url":"https://arxiv.org/abs/2409.09144v1","paper_title":"PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage","code":"https://github.com/vislearn/PrimeDepth","n_code_links":1,"syntology":{"n_ran":13,"n_unverified":2,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"Metric3Dv2(L, FT)","metrics":{"Delta < 1.25":"0.989","Delta < 1.25^2":"0.998","Delta < 1.25^3":"1.000","RMSE":"0.183","absolute relative error":"0.047","log 10":"0.020"},"uses_additional_data":true,"paper_date":"2024-03-22","paper":"/paper/metric3d-v2-a-versatile-monocular-geometric-1","paper_url":"https://arxiv.org/abs/2404.15506v4","paper_title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","code":"https://github.com/yvanyin/metric3d","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"DepthMaster","metrics":{"Delta < 1.25":"0.972","absolute relative error":"0.050"},"uses_additional_data":true,"paper_date":"2025-01-05","paper":"/paper/depthmaster-taming-diffusion-models-for","paper_url":"https://arxiv.org/abs/2501.02576v1","paper_title":"DepthMaster: Taming Diffusion Models for Monocular Depth Estimation","code":"https://github.com/indu1ge/DepthMaster","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"GRIN","metrics":{"RMSE":"0.251","absolute relative error":"0.051"},"uses_additional_data":true,"paper_date":"2024-09-15","paper":"/paper/grin-zero-shot-metric-depth-with-pixel-level","paper_url":"https://arxiv.org/abs/2409.09896v1","paper_title":"GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"Marigold + E2E FT(zero-shot)","metrics":{"Delta < 1.25":"0.966","absolute relative error":"0.052"},"uses_additional_data":false,"paper_date":"2024-09-17","paper":"/paper/fine-tuning-image-conditional-diffusion","paper_url":"https://arxiv.org/abs/2409.11355v1","paper_title":"Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think","code":"https://github.com/VisualComputingInstitute/diffusion-e2e-ft","n_code_links":1,"syntology":{"n_ran":16,"n_unverified":1,"n_samples":17,"n_pointer_only_licence":17}},{"rank_in_archive_order":10,"model":"Marigold","metrics":{"Delta < 1.25":"0.964","Delta < 1.25^2":"0.991","Delta < 1.25^3":"0.998","RMSE":"0.224","absolute relative error":"0.055","log 10":"0.024"},"uses_additional_data":true,"paper_date":"2023-12-04","paper":"/paper/repurposing-diffusion-based-image-generators","paper_url":"https://arxiv.org/abs/2312.02145v2","paper_title":"Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation","code":"https://github.com/prs-eth/marigold","n_code_links":4,"syntology":{"n_ran":14,"n_unverified":12,"n_samples":26,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"Depth Anything","metrics":{"Delta < 1.25":"0.984","Delta < 1.25^2":"0.998","Delta < 1.25^3":"1.000","RMSE":"0.206","absolute relative error":"0.056","log 10":"0.024"},"uses_additional_data":true,"paper_date":"2024-01-19","paper":"/paper/depth-anything-unleashing-the-power-of-large","paper_url":"https://arxiv.org/abs/2401.10891v2","paper_title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","code":"https://github.com/LiheYoung/Depth-Anything","n_code_links":7,"syntology":{"n_ran":3,"n_unverified":8,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"UniDepth (Zero-shot)","metrics":{"Delta < 1.25":"0.984","Delta < 1.25^2":"0.997","Delta < 1.25^3":"0.999","RMSE":"0.201","absolute relative error":"0.058","log 10":"0.024"},"uses_additional_data":true,"paper_date":"2024-03-27","paper":"/paper/unidepth-universal-monocular-metric-depth","paper_url":"https://arxiv.org/abs/2403.18913v1","paper_title":"UniDepth: Universal Monocular Metric Depth Estimation","code":"https://github.com/lpiccinelli-eth/unidepth","n_code_links":3,"syntology":{"n_ran":15,"n_unverified":11,"n_samples":26,"n_pointer_only_licence":25}},{"rank_in_archive_order":13,"model":"PrimeDepth","metrics":{"Delta < 1.25":"0.966","absolute relative error":"0.058"},"uses_additional_data":false,"paper_date":"2024-09-13","paper":"/paper/primedepth-efficient-monocular-depth","paper_url":"https://arxiv.org/abs/2409.09144v1","paper_title":"PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage","code":"https://github.com/vislearn/PrimeDepth","n_code_links":1,"syntology":{"n_ran":13,"n_unverified":2,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"ECoDepth","metrics":{"Delta < 1.25":"0.978","Delta < 1.25^2":"0.997","Delta < 1.25^3":"0.999","RMSE":"0.218","absolute relative error":"0.059","log 10":"0.026"},"uses_additional_data":false,"paper_date":"2024-03-27","paper":"/paper/ecodepth-effective-conditioning-of-diffusion","paper_url":"https://arxiv.org/abs/2403.18807v4","paper_title":"ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation","code":"https://github.com/aradhye2002/ecodepth","n_code_links":1,"syntology":{"n_ran":11,"n_unverified":4,"n_samples":15,"n_pointer_only_licence":15}},{"rank_in_archive_order":15,"model":"MetaPrompt-SD","metrics":{"Delta < 1.25":"0.976","Delta < 1.25^2":"0.997","Delta < 1.25^3":"0.999","RMSE":"0.223","absolute relative error":"0.061","log 10":"0.027"},"uses_additional_data":true,"paper_date":"2023-12-22","paper":"/paper/harnessing-diffusion-models-for-visual","paper_url":"https://arxiv.org/abs/2312.14733v1","paper_title":"Harnessing Diffusion Models for Visual Perception with Meta Prompts","code":"https://github.com/fudan-zvg/meta-prompts","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"EVP","metrics":{"Delta < 1.25":"0.976","Delta < 1.25^2":"0.997","Delta < 1.25^3":"0.999","RMSE":"0.224","absolute relative error":"0.061","log 10":"0.027"},"uses_additional_data":false,"paper_date":"2023-12-13","paper":"/paper/evp-enhanced-visual-perception-using-inverse","paper_url":"https://arxiv.org/abs/2312.08548v1","paper_title":"EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment","code":"https://github.com/lavreniuk/evp","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"TADP","metrics":{"Delta < 1.25":"0.976","Delta < 1.25^2":"0.997","Delta < 1.25^3":"0.999","RMSE":"0.225","absolute relative error":"0.062","log 10":"0.027"},"uses_additional_data":true,"paper_date":"2023-09-29","paper":"/paper/text-image-alignment-for-diffusion-based","paper_url":"https://arxiv.org/abs/2310.00031v3","paper_title":"Text-image Alignment for Diffusion-based Perception","code":"https://github.com/damaggu/tadp","n_code_links":2,"syntology":null},{"rank_in_archive_order":18,"model":"FutureDepth","metrics":{"Delta < 1.25":"0.981","Delta < 1.25^2":"0.996","Delta < 1.25^3":"0.999","RMSE":"0.233","absolute relative error":"0.063","log 10":"0.027"},"uses_additional_data":false,"paper_date":"2024-03-19","paper":"/paper/futuredepth-learning-to-predict-the-future","paper_url":"https://arxiv.org/abs/2403.12953v2","paper_title":"FutureDepth: Learning to Predict the Future Improves Video Depth Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"MeSa","metrics":{"Delta < 1.25":"0.964","Delta < 1.25^2":"0.995","Delta < 1.25^3":"0.999","RMSE":"0.238","absolute relative error":"0.066","log 10":"0.029"},"uses_additional_data":false,"paper_date":"2023-10-06","paper":"/paper/mesa-masked-geometric-and-supervised-pre","paper_url":"https://arxiv.org/abs/2310.04551v1","paper_title":"MeSa: Masked, Geometric, and Supervised Pre-training for Monocular Depth Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"PolyMaX(ConvNeXt-L)","metrics":{"Delta < 1.25":"0.969","Delta < 1.25^2":"0.9958","Delta < 1.25^3":"0.999","RMSE":"0.25","absolute relative error":"0.067","log 10":"0.029"},"uses_additional_data":true,"paper_date":"2023-11-09","paper":"/paper/polymax-general-dense-prediction-with-mask","paper_url":"https://arxiv.org/abs/2311.05770v1","paper_title":"PolyMaX: General Dense Prediction with Mask Transformer","code":"https://github.com/google-research/deeplab2","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"VPD","metrics":{"Delta < 1.25":"0.964","Delta < 1.25^2":"0.995","Delta < 1.25^3":"0.999","RMSE":"0.254","absolute relative error":"0.069","log 10":"0.030"},"uses_additional_data":false,"paper_date":"2023-03-03","paper":"/paper/unleashing-text-to-image-diffusion-models-for-1","paper_url":"https://arxiv.org/abs/2303.02153v1","paper_title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","code":"https://github.com/open-mmlab/mmsegmentation/tree/main/configs/vpd","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"NVDS(DPT-L)","metrics":{"Delta < 1.25":"0.9493","Delta < 1.25^2":"0.991","Delta < 1.25^3":"0.997","RMSE":"0.282","absolute relative error":"0.072","log 10":"0.031"},"uses_additional_data":true,"paper_date":"2023-07-17","paper":"/paper/neural-video-depth-stabilizer","paper_url":"https://arxiv.org/abs/2307.08695v3","paper_title":"NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation","code":"https://github.com/raymondwang987/nvds","n_code_links":2,"syntology":null},{"rank_in_archive_order":23,"model":"DMD","metrics":{"Delta < 1.25":"0.953","Delta < 1.25^2":"0.989","Delta < 1.25^3":"0.996","RMSE":"0.296","absolute relative error":"0.072","log 10":"0.031"},"uses_additional_data":true,"paper_date":"2023-12-20","paper":"/paper/zero-shot-metric-depth-with-a-field-of-view","paper_url":"https://arxiv.org/abs/2312.13252v1","paper_title":"Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Model","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":24,"model":"ScaleDepth-N","metrics":{"Delta < 1.25":"0.957","Delta < 1.25^2":"0.994","Delta < 1.25^3":"0.999","RMSE":"0.267","absolute relative error":"0.074","log 10":"0.032"},"uses_additional_data":false,"paper_date":"2024-07-11","paper":"/paper/scaledepth-decomposing-metric-depth","paper_url":"https://arxiv.org/abs/2407.08187v1","paper_title":"ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation","code":"https://github.com/RuijieZhu94/mmdepth/blob/main/projects/ScaleDepth/README.md","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"DepthGen","metrics":{"Delta < 1.25":"0.946","Delta < 1.25^2":"0.987","Delta < 1.25^3":" 0.996","RMSE":"0.314","absolute relative error":"0.074","log 10":"0.032"},"uses_additional_data":true,"paper_date":"2023-02-28","paper":"/paper/monocular-depth-estimation-using-diffusion","paper_url":"https://arxiv.org/abs/2302.14816v1","paper_title":"Monocular Depth Estimation using Diffusion Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":26,"model":"ZoeD-M12-N","metrics":{"Delta < 1.25":"0.955","Delta < 1.25^2":"0.995","Delta < 1.25^3":"0.999","RMSE":"0.270","absolute relative error":"0.075","log 10":"0.032"},"uses_additional_data":true,"paper_date":"2023-02-23","paper":"/paper/zoedepth-zero-shot-transfer-by-combining","paper_url":"https://arxiv.org/abs/2302.12288v1","paper_title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","code":"https://github.com/isl-org/MiDaS","n_code_links":6,"syntology":{"n_ran":10,"n_unverified":6,"n_samples":16,"n_pointer_only_licence":1}},{"rank_in_archive_order":27,"model":"AiT-P(SwinV2-L)","metrics":{"Delta < 1.25":"0.954","Delta < 1.25^2":"0.994","Delta < 1.25^3":"0.999","RMSE":"0.275","absolute relative error":"0.076","log 10":"0.033"},"uses_additional_data":false,"paper_date":"2023-01-05","paper":"/paper/all-in-tokens-unifying-output-space-of-visual","paper_url":"https://arxiv.org/abs/2301.02229v2","paper_title":"All in Tokens: Unifying Output Space of Visual Tasks via Soft Token","code":"https://github.com/swintransformer/ait","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"Gaming for Depth (GfD)","metrics":{"Delta < 1.25":"0.931","Delta < 1.25^2":"0.986","Delta < 1.25^3":"0.996","RMSE":"0.364","absolute relative error":"0.080","log 10":"0.033"},"uses_additional_data":true,"paper_date":"2023-09-18","paper":"/paper/large-scale-monocular-depth-estimation-in-the","paper_url":"https://www.sciencedirect.com/science/article/abs/pii/S0952197623013738","paper_title":"Large-scale Monocular Depth Estimation in the Wild","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":29,"model":"SwinV2-L 1K-MIM","metrics":{"Delta < 1.25":"0.949","Delta < 1.25^2":"0.994","Delta < 1.25^3":"0.999","RMSE":"0.287","absolute relative error":"0.083","log 10":"0.035"},"uses_additional_data":false,"paper_date":"2022-05-26","paper":"/paper/revealing-the-dark-secrets-of-masked-image","paper_url":"https://arxiv.org/abs/2205.13543v2","paper_title":"Revealing the Dark Secrets of Masked Image Modeling","code":"https://github.com/SwinTransformer/MIM-Depth-Estimation","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"Metric3D (ConvNeXt-Large, Zero-shot testing)","metrics":{"Delta < 1.25":"0.944","Delta < 1.25^2":"0.986","Delta < 1.25^3":"0.995","RMSE":"0.310","absolute relative error":"0.083","log 10":"0.035"},"uses_additional_data":true,"paper_date":"2023-07-20","paper":"/paper/metric3d-towards-zero-shot-metric-3d","paper_url":"https://arxiv.org/abs/2307.10984v1","paper_title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","code":"https://github.com/yvanyin/metric3d","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"VA-DepthNet(SwinV1-L)","metrics":{"Delta < 1.25":"0.937","Delta < 1.25^2":"0.992","Delta < 1.25^3":"0.999","RMSE":"0.304","absolute relative error":"0.086","log 10":"0.037"},"uses_additional_data":false,"paper_date":"2023-02-13","paper":"/paper/va-depthnet-a-variational-approach-to-single","paper_url":"https://arxiv.org/abs/2302.06556v2","paper_title":"VA-DepthNet: A Variational Approach to Single Image Depth Prediction","code":"https://github.com/cnexah/va-depthnet","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"iDisc","metrics":{"Delta < 1.25^2":"0.993","Delta < 1.25^3":"0.999","absolute relative error":"0.086"},"uses_additional_data":false,"paper_date":"2023-04-13","paper":"/paper/idisc-internal-discretization-for-monocular","paper_url":"https://arxiv.org/abs/2304.06334v1","paper_title":"iDisc: Internal Discretization for Monocular Depth Estimation","code":"https://github.com/lpiccinelli-eth/unidepth","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":33,"model":"MIM-Swin-V2","metrics":{"Delta < 1.25":"0.9361","Delta < 1.25^2":"0.9916","Delta < 1.25^3":"0.9981","RMSE":"0.3046","absolute relative error":"0.0864","log 10":"0.0365"},"uses_additional_data":false,"paper_date":"2023-11-07","paper":"/paper/analysis-of-nan-divergence-in-training","paper_url":"https://arxiv.org/abs/2311.03938v1","paper_title":"Analysis of NaN Divergence in Training Monocular Depth Estimation Model","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":34,"model":"NDDepth","metrics":{"Delta < 1.25":"0.936","Delta < 1.25^2":"0.991","Delta < 1.25^3":"0.998","RMSE":"0.311","absolute relative error":"0.087","log 10":"0.038"},"uses_additional_data":false,"paper_date":"2023-09-19","paper":"/paper/nddepth-normal-distance-assisted-monocular","paper_url":"https://arxiv.org/abs/2309.10592v2","paper_title":"NDDepth: Normal-Distance Assisted Monocular Depth Estimation","code":"https://github.com/ShuweiShao/NDDepth","n_code_links":1,"syntology":null},{"rank_in_archive_order":35,"model":"IEBins","metrics":{"Delta < 1.25":"0.936","Delta < 1.25^2":"0.992","Delta < 1.25^3":"0.998","RMSE":"0.314","absolute relative error":"0.087","log 10":"0.038"},"uses_additional_data":false,"paper_date":"2023-09-25","paper":"/paper/iebins-iterative-elastic-bins-for-monocular-1","paper_url":"https://arxiv.org/abs/2309.14137v1","paper_title":"IEBins: Iterative Elastic Bins for Monocular Depth Estimation","code":"https://github.com/shuweishao/iebins","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":5,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":36,"model":"URCDC-Depth","metrics":{"Delta < 1.25":"0.933","Delta < 1.25^2":"0.992","Delta < 1.25^3":"0.998","RMSE":"0.316","absolute relative error":"0.088","log 10":"0.038"},"uses_additional_data":false,"paper_date":"2023-02-16","paper":"/paper/urcdc-depth-uncertainty-rectified-cross","paper_url":"https://arxiv.org/abs/2302.08149v2","paper_title":"URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation","code":"https://github.com/shuweishao/urcdc-depth","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":37,"model":"OrdinalEntropy","metrics":{"Delta < 1.25":"0.932","RMSE":"0.321","absolute relative error":"0.089","log 10":"0.039"},"uses_additional_data":false,"paper_date":"2023-01-21","paper":"/paper/improving-deep-regression-with-ordinal","paper_url":"https://arxiv.org/abs/2301.08915v3","paper_title":"Improving Deep Regression with Ordinal Entropy","code":"https://github.com/needylove/ordinalentropy","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":38,"model":"PixelFormer","metrics":{"Delta < 1.25":"0.929","Delta < 1.25^2":"0.991","Delta < 1.25^3":"0.998","RMSE":"0.322","absolute relative error":"0.090","log 10":"0.039"},"uses_additional_data":false,"paper_date":"2022-10-17","paper":"/paper/attention-attention-everywhere-monocular","paper_url":"https://arxiv.org/abs/2210.09071v1","paper_title":"Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention","code":"https://github.com/ashutosh1807/pixelformer","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":39,"model":"LeReS","metrics":{"Delta < 1.25":"0.916","absolute relative error":"0.09"},"uses_additional_data":true,"paper_date":"2020-12-17","paper":"/paper/learning-to-recover-3d-scene-shape-from-a","paper_url":"https://arxiv.org/abs/2012.09365v1","paper_title":"Learning to Recover 3D Scene Shape from a Single Image","code":"https://github.com/aim-uofa/AdelaiDepth","n_code_links":1,"syntology":null},{"rank_in_archive_order":40,"model":"DINOv2 (ViT-g/14 frozen, w/ DPT decoder)","metrics":{"Delta < 1.25":"0.9497","Delta < 1.25^2":"0.996","Delta < 1.25^3":"0.9994","RMSE":"0.279","absolute relative error":"0.0907","log 10":"0.0371"},"uses_additional_data":true,"paper_date":"2023-04-14","paper":"/paper/dinov2-learning-robust-visual-features","paper_url":"https://arxiv.org/abs/2304.07193v2","paper_title":"DINOv2: Learning Robust Visual Features without Supervision","code":"https://github.com/huggingface/transformers","n_code_links":26,"syntology":{"n_ran":21,"n_unverified":25,"n_samples":46,"n_pointer_only_licence":12}},{"rank_in_archive_order":41,"model":"DDP (step3)","metrics":{"Delta < 1.25":"0.921","Delta < 1.25^2":"0.990","Delta < 1.25^3":"0.998","RMSE":"0.329","absolute relative error":"0.094","log 10":"0.040"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/ddp-diffusion-model-for-dense-visual","paper_url":"https://arxiv.org/abs/2303.17559v2","paper_title":"DDP: Diffusion Model for Dense Visual Prediction","code":"https://github.com/jiyuanfeng/ddp","n_code_links":1,"syntology":null},{"rank_in_archive_order":42,"model":"BinsFormer","metrics":{"Delta < 1.25":"0.925","Delta < 1.25^2":"0.989","Delta < 1.25^3":"0.997","RMSE":"0.330","absolute relative error":"0.094","log 10":"0.040"},"uses_additional_data":false,"paper_date":"2022-04-03","paper":"/paper/binsformer-revisiting-adaptive-bins-for","paper_url":"https://arxiv.org/abs/2204.00987v1","paper_title":"BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation","code":"https://github.com/zhyever/monocular-depth-estimation-toolbox","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":43,"model":"NeWCRFs","metrics":{"Delta < 1.25":"0.922","Delta < 1.25^2":"0.992","Delta < 1.25^3":"0.998","RMSE":"0.334","absolute relative error":"0.095","log 10":"0.041"},"uses_additional_data":false,"paper_date":"2022-03-03","paper":"/paper/new-crfs-neural-window-fully-connected-crfs-1","paper_url":"https://arxiv.org/abs/2203.01502v2","paper_title":"NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation","code":"https://github.com/aliyun/NeWCRFs","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":10}},{"rank_in_archive_order":44,"model":"D-Net","metrics":{"Delta < 1.25":"0.919","Delta < 1.25^2":"0.988","Delta < 1.25^3":"0.997","RMSE":"0.354","absolute relative error":"0.095","log 10":"0.041"},"uses_additional_data":false,"paper_date":"2021-09-29","paper":"/paper/d-net-a-generalised-and-optimised-deep","paper_url":"https://ieeexplore.ieee.org/document/9551940","paper_title":"D-Net: A Generalised and Optimised Deep Network for Monocular Depth Estimation","code":"https://github.com/Joshuat38/D-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"DepthFormer","metrics":{"Delta < 1.25":"0.921","Delta < 1.25^2":"0.989","Delta < 1.25^3":"0.998","RMSE":"0.339","absolute relative error":"0.096","log 10":"0.041"},"uses_additional_data":false,"paper_date":"2022-03-27","paper":"/paper/depthformer-exploiting-long-range-correlation","paper_url":"https://arxiv.org/abs/2203.14211v1","paper_title":"DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation","code":"https://github.com/zhyever/Monocular-Depth-Estimation-Toolbox/tree/main/configs/depthformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":46,"model":"GLPDepth","metrics":{"Delta < 1.25":"0.915","Delta < 1.25^2":"0.988","Delta < 1.25^3":"0.997","RMSE":"0.344","absolute relative error":"0.098","log 10":"0.042"},"uses_additional_data":false,"paper_date":"2022-01-19","paper":"/paper/global-local-path-networks-for-monocular","paper_url":"https://arxiv.org/abs/2201.07436v3","paper_title":"Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth","code":"https://github.com/huggingface/transformers","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":47,"model":"LocalBins","metrics":{"Delta < 1.25":"0.91","Delta < 1.25^2":"0.986","Delta < 1.25^3":"0.997","RMSE":"0.351","absolute relative error":"0.098","log 10":"0.042"},"uses_additional_data":false,"paper_date":"2022-03-28","paper":"/paper/localbins-improving-depth-estimation-by","paper_url":"https://arxiv.org/abs/2203.15132v1","paper_title":"LocalBins: Improving Depth Estimation by Learning Local Distributions","code":"https://github.com/shariqfarooq123/localbins","n_code_links":1,"syntology":{"n_ran":11,"n_unverified":3,"n_samples":14,"n_pointer_only_licence":14}},{"rank_in_archive_order":48,"model":"Depth-Map-Decomposition-HRWSI","metrics":{"Delta < 1.25":"0.913","Delta < 1.25^2":"0.987","Delta < 1.25^3":"0.998","RMSE":"0.355","absolute relative error":"0.098","log 10":"0.042"},"uses_additional_data":true,"paper_date":"2022-08-23","paper":"/paper/depth-map-decomposition-for-monocular-depth","paper_url":"https://arxiv.org/abs/2208.10762v1","paper_title":"Depth Map Decomposition for Monocular Depth Estimation","code":"https://github.com/jyjunmcl/Depth-Map-Decomposition","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":49,"model":"Depthformer","metrics":{"Delta < 1.25":"0.913","Delta < 1.25^2":"0.988","Delta < 1.25^3":"0.997","RMSE":"0.345","absolute relative error":"0.100","log 10":"0.042"},"uses_additional_data":false,"paper_date":"2022-07-10","paper":"/paper/depthformer-multiscale-vision-transformer-for","paper_url":"https://arxiv.org/abs/2207.04535v2","paper_title":"Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information Fusion","code":"https://github.com/ashutosh1807/depthformer","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":50,"model":"Depth-Map-Decomposition","metrics":{"Delta < 1.25":"0.907","Delta < 1.25^2":"0.986","Delta < 1.25^3":"0.997","RMSE":"0.362","absolute relative error":"0.100","log 10":"0.043"},"uses_additional_data":false,"paper_date":"2022-08-23","paper":"/paper/depth-map-decomposition-for-monocular-depth","paper_url":"https://arxiv.org/abs/2208.10762v1","paper_title":"Depth Map Decomposition for Monocular Depth Estimation","code":"https://github.com/jyjunmcl/Depth-Map-Decomposition","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":51,"model":"IronDepth","metrics":{"Delta < 1.25":"0.910","Delta < 1.25^2":"0.985","Delta < 1.25^3":"0.997","RMSE":"0.352","absolute relative error":"0.101","log 10":"0.043"},"uses_additional_data":false,"paper_date":"2022-10-07","paper":"/paper/irondepth-iterative-refinement-of-single-view","paper_url":"https://arxiv.org/abs/2210.03676v1","paper_title":"IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty","code":"https://github.com/baegwangbin/irondepth","n_code_links":1,"syntology":null},{"rank_in_archive_order":52,"model":"AdaBins","metrics":{"Delta < 1.25":"0.903","Delta < 1.25^2":"0.984","Delta < 1.25^3":"0.997","RMSE":"0.364","absolute relative error":"0.103","log 10":"0.044"},"uses_additional_data":false,"paper_date":"2020-11-28","paper":"/paper/adabins-depth-estimation-using-adaptive-bins","paper_url":"https://arxiv.org/abs/2011.14141v1","paper_title":"AdaBins: Depth Estimation using Adaptive Bins","code":"https://github.com/shariqfarooq123/AdaBins","n_code_links":11,"syntology":null},{"rank_in_archive_order":53,"model":"P3Depth","metrics":{"Delta < 1.25":"0.898","Delta < 1.25^2":"0.981","Delta < 1.25^3":"0.996","RMSE":"0.356","absolute relative error":"0.104","log 10":"0.043"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/p3depth-monocular-depth-estimation-with-a","paper_url":"https://arxiv.org/abs/2204.02091v1","paper_title":"P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior","code":"https://github.com/syscv/p3depth","n_code_links":1,"syntology":null},{"rank_in_archive_order":54,"model":"CutDepth","metrics":{"Delta < 1.25":"0.899","Delta < 1.25^2":"0.985","Delta < 1.25^3":"0.997","RMSE":"0.375","absolute relative error":"0.104","log 10":"0.044"},"uses_additional_data":true,"paper_date":"2021-07-16","paper":"/paper/cutdepth-edge-aware-data-augmentation-in","paper_url":"https://arxiv.org/abs/2107.07684v1","paper_title":"CutDepth:Edge-aware Data Augmentation in Depth Estimation","code":"https://github.com/aradhye2002/ecodepth","n_code_links":1,"syntology":null},{"rank_in_archive_order":55,"model":"LapDepth","metrics":{"Delta < 1.25":"0.895","Delta < 1.25^2":"0.983","Delta < 1.25^3":"0.996","RMSE":"0.384","absolute relative error":"0.105","log 10":"0.045"},"uses_additional_data":false,"paper_date":"2021-01-08","paper":"/paper/monocular-depth-estimation-using-laplacian","paper_url":"https://ieeexplore.ieee.org/document/9316778","paper_title":"Monocular Depth Estimation Using Laplacian Pyramid-Based Depth Residuals","code":"https://github.com/tjqansthd/LapDepth-release","n_code_links":1,"syntology":null},{"rank_in_archive_order":56,"model":"DPT-Hybrid","metrics":{"Delta < 1.25":"0.904","Delta < 1.25^2":"0.988","Delta < 1.25^3":"0.994","RMSE":"0.357","absolute relative error":"0.110","log 10":"0.045"},"uses_additional_data":true,"paper_date":"2021-03-24","paper":"/paper/vision-transformers-for-dense-prediction","paper_url":"https://arxiv.org/abs/2103.13413v1","paper_title":"Vision Transformers for Dense Prediction","code":"https://github.com/huggingface/transformers","n_code_links":15,"syntology":{"n_ran":54,"n_unverified":62,"n_samples":116,"n_pointer_only_licence":15}},{"rank_in_archive_order":57,"model":"VNL","metrics":{"Delta < 1.25":"0.875","Delta < 1.25^2":"0.976","Delta < 1.25^3":"0.989","RMSE":"0.416","absolute relative error":"0.111","log 10":"0.048"},"uses_additional_data":false,"paper_date":"2019-07-29","paper":"/paper/enforcing-geometric-constraints-of-virtual","paper_url":"https://arxiv.org/abs/1907.12209v2","paper_title":"Enforcing geometric constraints of virtual normal for depth prediction","code":"https://github.com/aim-uofa/AdelaiDepth","n_code_links":3,"syntology":null},{"rank_in_archive_order":58,"model":"Focal-WNet","metrics":{"Delta < 1.25":"0.875","Delta < 1.25^2":"0.980","Delta < 1.25^3":"0.995","RMSE":"0.398","absolute relative error":"0.116","log 10":"0.048"},"uses_additional_data":false,"paper_date":"2022-07-18","paper":"/paper/focal-wnet-an-architecture-unifying","paper_url":"https://ieeexplore.ieee.org/abstract/document/9824488","paper_title":"Focal-WNet: An Architecture Unifying Convolution and Attention for Depth Estimation","code":"https://github.com/Goubeast/Focal-WNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":59,"model":"SC-DepthV2","metrics":{"Delta < 1.25":"0.820","Delta < 1.25^2":"0.956","RMSE":"0.532","absolute relative error":"0.138","log 10":"0.059"},"uses_additional_data":false,"paper_date":"2020-06-04","paper":"/paper/unsupervised-depth-learning-in-challenging","paper_url":"https://arxiv.org/abs/2006.02708v2","paper_title":"Auto-Rectify Network for Unsupervised Indoor Depth Estimation","code":"https://github.com/JiawangBian/sc_depth_pl","n_code_links":1,"syntology":null},{"rank_in_archive_order":60,"model":"NVS-MonoDepth","metrics":{"RMSE":"0.331"},"uses_additional_data":false,"paper_date":"2021-12-22","paper":"/paper/nvs-monodepth-improving-monocular-depth","paper_url":"https://arxiv.org/abs/2112.12577v1","paper_title":"NVS-MonoDepth: Improving Monocular Depth Prediction with Novel View Synthesis","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":61,"model":"BTS","metrics":{"Delta < 1.25^3":"0.995","RMSE":"0.392"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/from-big-to-small-multi-scale-local-planar","paper_url":"https://arxiv.org/abs/1907.10326v6","paper_title":"From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation","code":"https://github.com/cleinc/bts","n_code_links":14,"syntology":{"n_ran":5,"n_unverified":10,"n_samples":15,"n_pointer_only_licence":4}},{"rank_in_archive_order":62,"model":"DSN","metrics":{"RMSE":"0.429"},"uses_additional_data":true,"paper_date":"2020-10-13","paper":"/paper/on-deep-learning-techniques-to-boost","paper_url":"https://arxiv.org/abs/2010.06626v2","paper_title":"On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":63,"model":"DenseDepth","metrics":{"RMSE":"0.465"},"uses_additional_data":false,"paper_date":"2018-12-31","paper":"/paper/high-quality-monocular-depth-estimation-via","paper_url":"http://arxiv.org/abs/1812.11941v2","paper_title":"High Quality Monocular Depth Estimation via Transfer Learning","code":"https://github.com/ialhashim/DenseDepth","n_code_links":45,"syntology":{"n_ran":5,"n_unverified":18,"n_samples":23,"n_pointer_only_licence":3}},{"rank_in_archive_order":64,"model":"ACAN","metrics":{"RMSE":"0.496"},"uses_additional_data":false,"paper_date":"2019-01-29","paper":"/paper/attention-based-context-aggregation-network","paper_url":"http://arxiv.org/abs/1901.10137v1","paper_title":"Attention-based Context Aggregation Network for Monocular Depth Estimation","code":"https://github.com/miraiaroha/ACAN","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":12,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":65,"model":"SharpNet","metrics":{"RMSE":"0.496"},"uses_additional_data":false,"paper_date":"2019-05-21","paper":"/paper/190508598","paper_url":"https://arxiv.org/abs/1905.08598v3","paper_title":"SharpNet: Fast and Accurate Recovery of Occluding Contours in Monocular Depth Estimation","code":"https://github.com/MichaelRamamonjisoa/SharpNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":66,"model":"PAP-Depth","metrics":{"RMSE":"0.497"},"uses_additional_data":false,"paper_date":"2019-06-08","paper":"/paper/pattern-affinitive-propagation-across-depth-1","paper_url":"https://arxiv.org/abs/1906.03525v1","paper_title":"Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":67,"model":"SDC-Depth","metrics":{"RMSE":"0.497"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/sdc-depth-semantic-divide-and-conquer-network","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Wang_SDC-Depth_Semantic_Divide-and-Conquer_Network_for_Monocular_Depth_Estimation_CVPR_2020_paper.html","paper_title":"SDC-Depth: Semantic Divide-and-Conquer Network for Monocular Depth Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":68,"model":"DORN","metrics":{"RMSE":"0.509"},"uses_additional_data":false,"paper_date":"2018-06-06","paper":"/paper/deep-ordinal-regression-network-for-monocular","paper_url":"http://arxiv.org/abs/1806.02446v1","paper_title":"Deep Ordinal Regression Network for Monocular Depth Estimation","code":"https://github.com/hufu6371/DORN","n_code_links":5,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":69,"model":"SARPN","metrics":{"RMSE":"0.514"},"uses_additional_data":false,"paper_date":"2019-07-13","paper":"/paper/structure-aware-residual-pyramid-network-for","paper_url":"https://arxiv.org/abs/1907.06023v1","paper_title":"Structure-Aware Residual Pyramid Network for Monocular Depth Estimation","code":"https://github.com/Xt-Chen/SARPN","n_code_links":1,"syntology":null},{"rank_in_archive_order":70,"model":"InvPT","metrics":{"RMSE":"0.5183"},"uses_additional_data":false,"paper_date":"2022-03-15","paper":"/paper/inverted-pyramid-multi-task-transformer-for","paper_url":"https://arxiv.org/abs/2203.07997v3","paper_title":"InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding","code":"https://github.com/prismformore/InvPT","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":71,"model":"FastDenseNas-arch0","metrics":{"RMSE":"0.523"},"uses_additional_data":false,"paper_date":"2018-10-25","paper":"/paper/fast-neural-architecture-search-of-compact","paper_url":"https://arxiv.org/abs/1810.10804v3","paper_title":"Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells","code":"https://github.com/mindspore-ai/models/tree/master/research/cv/adelaide_ea","n_code_links":4,"syntology":null},{"rank_in_archive_order":72,"model":"FastDenseNas-arch2","metrics":{"RMSE":"0.525"},"uses_additional_data":false,"paper_date":"2018-10-25","paper":"/paper/fast-neural-architecture-search-of-compact","paper_url":"https://arxiv.org/abs/1810.10804v3","paper_title":"Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells","code":"https://github.com/mindspore-ai/models/tree/master/research/cv/adelaide_ea","n_code_links":4,"syntology":null},{"rank_in_archive_order":73,"model":"FastDenseNas-arch1","metrics":{"RMSE":"0.526"},"uses_additional_data":false,"paper_date":"2018-10-25","paper":"/paper/fast-neural-architecture-search-of-compact","paper_url":"https://arxiv.org/abs/1810.10804v3","paper_title":"Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells","code":"https://github.com/mindspore-ai/models/tree/master/research/cv/adelaide_ea","n_code_links":4,"syntology":null},{"rank_in_archive_order":74,"model":"SENet-154","metrics":{"RMSE":"0.530"},"uses_additional_data":false,"paper_date":"2018-03-23","paper":"/paper/revisiting-single-image-depth-estimation","paper_url":"http://arxiv.org/abs/1803.08673v2","paper_title":"Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries","code":"https://github.com/JunjH/Revisiting_Single_Depth_Estimation","n_code_links":4,"syntology":null},{"rank_in_archive_order":75,"model":"ProbMonoDepth","metrics":{"RMSE":"0.536"},"uses_additional_data":false,"paper_date":"2019-06-13","paper":"/paper/generating-and-exploiting-probabilistic","paper_url":"https://arxiv.org/abs/1906.05739v2","paper_title":"Generating and Exploiting Probabilistic Monocular Depth Estimates","code":"https://github.com/likesum/prdepth","n_code_links":1,"syntology":null},{"rank_in_archive_order":76,"model":"RelativeDepth","metrics":{"RMSE":"0.538"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/monocular-depth-estimation-using-relative","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Lee_Monocular_Depth_Estimation_Using_Relative_Depth_Maps_CVPR_2019_paper.html","paper_title":"Monocular Depth Estimation Using Relative Depth Maps","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":77,"model":"PGT (Swin-S)","metrics":{"RMSE":"0.5468"},"uses_additional_data":false,"paper_date":"2023-07-28","paper":"/paper/prompt-guided-transformer-for-multi-task","paper_url":"https://arxiv.org/abs/2307.15362v1","paper_title":"Prompt Guided Transformer for Multi-Task Dense Prediction","code":"https://github.com/innovator-zero/MTDP_Lib","n_code_links":1,"syntology":null},{"rank_in_archive_order":78,"model":"Index Network","metrics":{"RMSE":"0.565"},"uses_additional_data":false,"paper_date":"2019-08-11","paper":"/paper/index-network","paper_url":"https://arxiv.org/abs/1908.09895v2","paper_title":"Index Network","code":"https://github.com/poppinace/indexnet_matting","n_code_links":6,"syntology":null},{"rank_in_archive_order":79,"model":"Multi-Task Light-Weight-RefineNet","metrics":{"RMSE":"0.565"},"uses_additional_data":false,"paper_date":"2018-09-13","paper":"/paper/real-time-joint-semantic-segmentation-and","paper_url":"http://arxiv.org/abs/1809.04766v2","paper_title":"Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations","code":"https://github.com/DrSleep/multi-task-refinenet","n_code_links":4,"syntology":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":80,"model":"DeepLabV3+ (F10)","metrics":{"RMSE":"0.575"},"uses_additional_data":false,"paper_date":"2020-01-14","paper":"/paper/single-image-depth-estimation-trained-via-1","paper_url":"https://arxiv.org/abs/2001.05036v1","paper_title":"Single Image Depth Estimation Trained via Depth from Defocus Cues","code":"https://github.com/shirgur/UnsupervisedDepthFromFocus","n_code_links":1,"syntology":null},{"rank_in_archive_order":81,"model":"Xu et al.","metrics":{"RMSE":"0.586"},"uses_additional_data":false,"paper_date":"2017-04-07","paper":"/paper/multi-scale-continuous-crfs-as-sequential","paper_url":"http://arxiv.org/abs/1704.02157v1","paper_title":"Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation","code":"https://github.com/danxuhk/ContinuousCRF-CNN","n_code_links":2,"syntology":null},{"rank_in_archive_order":82,"model":"PGT (Swin-T)","metrics":{"RMSE":"0.59"},"uses_additional_data":false,"paper_date":"2023-07-28","paper":"/paper/prompt-guided-transformer-for-multi-task","paper_url":"https://arxiv.org/abs/2307.15362v1","paper_title":"Prompt Guided Transformer for Multi-Task Dense Prediction","code":"https://github.com/innovator-zero/MTDP_Lib","n_code_links":1,"syntology":null},{"rank_in_archive_order":83,"model":"SOM","metrics":{"RMSE":"0.604"},"uses_additional_data":false,"paper_date":"2019-09-10","paper":"/paper/structure-attentioned-memory-network-for","paper_url":"https://arxiv.org/abs/1909.04594v1","paper_title":"Structure-Attentioned Memory Network for Monocular Depth Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":84,"model":"Li et al.","metrics":{"RMSE":"0.635"},"uses_additional_data":false,"paper_date":"2016-07-04","paper":"/paper/a-two-streamed-network-for-estimating-fine","paper_url":"http://arxiv.org/abs/1607.00730v4","paper_title":"A Two-Streamed Network for Estimating Fine-Scaled Depth Maps from Single RGB Images","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":85,"model":"Eigen et al.","metrics":{"RMSE":"0.641"},"uses_additional_data":false,"paper_date":"2014-11-18","paper":"/paper/predicting-depth-surface-normals-and-semantic","paper_url":"http://arxiv.org/abs/1411.4734v4","paper_title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","code":"https://github.com/yhlleo/DeepSegmentor","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":37,"rows_with_any_sample_ran":34,"distinct_papers_with_graph_line":35,"distinct_papers_with_any_sample_ran":32,"samples_over_distinct_papers":{"n_ran":254,"n_unverified":220,"n_samples":474,"n_pointer_only_licence":155,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":271,"n_unverified":223,"n_samples":494,"n_pointer_only_licence":155,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}