{"url":"/sota/monocular-depth-estimation-on-kitti-eigen-1","task":{"name":"Monocular Depth Estimation","url":"/task/monocular-depth-estimation","note":null},"dataset":{"name":"KITTI Eigen split unsupervised","url":"/dataset/kitti"},"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","RMSE log","Sq Rel","Delta < 1.25","Delta < 1.25^2","Delta < 1.25^3","Resolution","Mono","Test frames"],"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","RMSE log":"lower","Sq Rel":null,"Delta < 1.25":null,"Delta < 1.25^2":null,"Delta < 1.25^3":null,"Resolution":null,"Mono":null,"Test frames":null}},"counts":{"rows":55,"rows_with_code":44,"rows_with_paper_page":55,"rows_dated":55,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SPIdepth","metrics":{"Delta < 1.25":"0.94","Delta < 1.25^2":"0.973","Delta < 1.25^3":"0.985","Mono":"X","RMSE":"3.662","RMSE log":"0.153","Resolution":"1024x320","Sq Rel":"0.531","Test frames":"1","absolute relative error":"0.071"},"uses_additional_data":false,"paper_date":"2024-04-18","paper":"/paper/spidepth-strengthened-pose-information-for","paper_url":"https://arxiv.org/abs/2404.12501v3","paper_title":"SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimation","code":"https://github.com/Lavreniuk/SPIdepth","n_code_links":1,"syntology":{"n_ran":13,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"PlaneDepth (S + 1280x384)","metrics":{"Delta < 1.25":"0.911","Delta < 1.25^2":"0.968","Delta < 1.25^3":"0.984","Mono":"X","RMSE":"3.981","RMSE log":"0.169","Resolution":"1280x384","Sq Rel":"0.549","absolute relative error":"0.084"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/planedepth-plane-based-self-supervised","paper_url":"https://arxiv.org/abs/2210.01612v3","paper_title":"PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes","code":"https://github.com/svip-lab/planedepth","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"ProDepth","metrics":{"Delta < 1.25":"0.918","Delta < 1.25^2":"0.969","Delta < 1.25^3":"0.984","Mono":"O","RMSE":"4.139","RMSE log":"0.166","Resolution":"640x192","Sq Rel":"0.629","Test frames":"2(-1,0)","absolute relative error":"0.086"},"uses_additional_data":false,"paper_date":"2024-07-12","paper":"/paper/prodepth-boosting-self-supervised-multi-frame","paper_url":"https://arxiv.org/abs/2407.09303v1","paper_title":"ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion","code":"https://github.com/sungmin-woo/ProDepth","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"Jasmine","metrics":{"Delta < 1.25":"0.919","Delta < 1.25^2":"0.972","Delta < 1.25^3":"0.986","Mono":"O","RMSE":"3.944","RMSE log":"0.161","Resolution":"1024x320","Sq Rel":"0.581","absolute relative error":"0.09"},"uses_additional_data":false,"paper_date":"2025-03-20","paper":"/paper/jasmine-harnessing-diffusion-prior-for-self","paper_url":"https://arxiv.org/abs/2503.15905v1","paper_title":"Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"SCIPaD","metrics":{"Delta < 1.25":"0.918","Delta < 1.25^2":"0.970","Delta < 1.25^3":"0.985","RMSE":"4.056","RMSE log":"0.166","Resolution":"640x192","Sq Rel":"0.650","absolute relative error":"0.090"},"uses_additional_data":false,"paper_date":"2024-07-07","paper":"/paper/scipad-incorporating-spatial-clues-into","paper_url":"https://arxiv.org/abs/2407.05283v1","paper_title":"SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning","code":"https://github.com/fengyi233/SCIPaD","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"DCPI-Depth (M+1024x320)","metrics":{"Delta < 1.25":"0.914","Delta < 1.25^2":"0.969","Delta < 1.25^3":"0.985","Mono":"O","RMSE":"4.113","RMSE log":"0.167","Sq Rel":"0.655","absolute relative error":"0.090"},"uses_additional_data":false,"paper_date":"2024-05-27","paper":"/paper/dcpi-depth-explicitly-infusing-dense","paper_url":"https://arxiv.org/abs/2405.16960v2","paper_title":"DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"EPCDepth(S+1024x320)","metrics":{"Delta < 1.25":"0.901","Delta < 1.25^2":"0.966","Delta < 1.25^3":"0.983","Mono":"X","RMSE":"4.207","RMSE log":"0.176","Resolution":"1024x320","Sq Rel":"0.646","absolute relative error":"0.091"},"uses_additional_data":false,"paper_date":"2021-09-26","paper":"/paper/excavating-the-potential-capacity-of-self","paper_url":"https://arxiv.org/abs/2109.12484v1","paper_title":"Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation","code":"https://github.com/prstrive/EPCDepth","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"Manydepth2(M+640x192)","metrics":{"Delta < 1.25":"0.909","Delta < 1.25^2":"0.968","Delta < 1.25^3":"0.984","Mono":"O","RMSE":"4.232","RMSE log":"0.170","Resolution":"640x192","Sq Rel":"0.649","absolute relative error":"0.091"},"uses_additional_data":false,"paper_date":"2023-12-23","paper":"/paper/mgdepth-motion-guided-cost-volume-for-self","paper_url":"https://arxiv.org/abs/2312.15268v8","paper_title":"Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic Scenes","code":"https://github.com/kaichen-z/rad","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":9,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"NimbleD-LiteMono-8M","metrics":{"Delta < 1.25":"0.910","Delta < 1.25^2":"0.970","Delta < 1.25^3":"0.986","Mono":"O","RMSE":"4.194","RMSE log":"0.165","Resolution":"640x192","Sq Rel":"0.646","absolute relative error":"0.092"},"uses_additional_data":false,"paper_date":"2024-08-26","paper":"/paper/nimbled-enhancing-self-supervised-monocular","paper_url":"https://arxiv.org/abs/2408.14177v1","paper_title":"NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training","code":"https://github.com/xapaxca/nimbled","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"MonoViT(MS+1024x320)","metrics":{"Delta < 1.25":"0.912","Delta < 1.25^2":"0.969","Delta < 1.25^3":"0.985","Mono":"X","RMSE":"4.202","RMSE log":"0.169","Resolution":"1024x320","Sq Rel":"0.671","absolute relative error":"0.093"},"uses_additional_data":false,"paper_date":"2022-08-06","paper":"/paper/monovit-self-supervised-monocular-depth","paper_url":"https://arxiv.org/abs/2208.03543v1","paper_title":"MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer","code":"https://github.com/zxcqlf/monovit","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"Manydepth2-NF(M+640x192)","metrics":{"Delta < 1.25":"0.909","Delta < 1.25^2":"0.968","Delta < 1.25^3":"0.985","Mono":"O","RMSE":"4.246","RMSE log":"0.170","Resolution":"640x192","Sq Rel":"0.676","absolute relative error":"0.094"},"uses_additional_data":false,"paper_date":"2023-12-23","paper":"/paper/mgdepth-motion-guided-cost-volume-for-self","paper_url":"https://arxiv.org/abs/2312.15268v8","paper_title":"Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic Scenes","code":"https://github.com/kaichen-z/rad","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":9,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"DIFFNet (MS+1024x320)","metrics":{"Delta < 1.25":"0.911","Delta < 1.25^2":"0.968","Delta < 1.25^3":"0.984","Mono":"X","RMSE":"4.250","RMSE log":"0.172","Sq Rel":"0.678","absolute relative error":"0.094"},"uses_additional_data":false,"paper_date":"2021-10-18","paper":"/paper/self-supervised-monocular-depthestimation","paper_url":"https://arxiv.org/abs/2110.09482v3","paper_title":"Self-Supervised Monocular Depth Estimation with Internal Feature Fusion","code":"https://github.com/brandleyzhou/diffnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"DCPI-Depth (M+640x192)","metrics":{"Delta < 1.25":"0.902","Delta < 1.25^2":"0.967","Delta < 1.25^3":"0.985","RMSE":"4.274","RMSE log":"0.170","Sq Rel":"0.662","absolute relative error":"0.095"},"uses_additional_data":false,"paper_date":"2024-05-27","paper":"/paper/dcpi-depth-explicitly-infusing-dense","paper_url":"https://arxiv.org/abs/2405.16960v2","paper_title":"DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"TransDSSL","metrics":{"Delta < 1.25":"0.906","Delta < 1.25^2":"0.967","Delta < 1.25^3":"0.984","Mono":"O","RMSE":"4.321","RMSE log":"0.172","Sq Rel":"0.711","absolute relative error":"0.095"},"uses_additional_data":false,"paper_date":"2022-08-05","paper":"/paper/transdssl-transformer-based-depth-estimation","paper_url":"https://ieeexplore.ieee.org/document/9851497","paper_title":"TransDSSL: Transformer based Depth Estimation via Self-Supervised Learning","code":"https://github.com/sejong-rcv/2021.Paper.TransDSSL","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"DS-Depth","metrics":{"Delta < 1.25":"0.905","Delta < 1.25^2":"0.966","Delta < 1.25^3":"0.984","RMSE":"4.329","RMSE log":"0.173","Sq Rel":"0.698","absolute relative error":"0.095"},"uses_additional_data":false,"paper_date":"2023-08-14","paper":"/paper/ds-depth-dynamic-and-static-depth-estimation","paper_url":"https://arxiv.org/abs/2308.07225v1","paper_title":"DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume","code":"https://github.com/xingy038/ds-depth","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"ProDepth(M+640x192)","metrics":{"Delta < 1.25":"0.902","Delta < 1.25^2":"0.967","Delta < 1.25^3":"0.985","Mono":"O","RMSE":"4.345","RMSE log":"0.172","Resolution":"640x192","Sq Rel":"0.693","absolute relative error":"0.095"},"uses_additional_data":false,"paper_date":"2024-07-12","paper":"/paper/prodepth-boosting-self-supervised-multi-frame","paper_url":"https://arxiv.org/abs/2407.09303v1","paper_title":"ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion","code":"https://github.com/sungmin-woo/ProDepth","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"CADepth-Net (MS+1024x320)","metrics":{"RMSE":"4.264","RMSE log":"0.173","Sq Rel":"0.694","absolute relative error":"0.096"},"uses_additional_data":false,"paper_date":"2021-12-24","paper":"/paper/channel-wise-attention-based-network-for-self","paper_url":"https://arxiv.org/abs/2112.13047v1","paper_title":"Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation","code":"https://github.com/kamiLight/CADepth-master","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":18,"model":"NimbleD-LiteMono","metrics":{"Delta < 1.25":"0.903","Delta < 1.25^2":"0.969","Delta < 1.25^3":"0.986","Mono":"O","RMSE":"4.304","RMSE log":"0.171","Resolution":"640x192","Sq Rel":"0.684","absolute relative error":"0.096"},"uses_additional_data":false,"paper_date":"2024-08-26","paper":"/paper/nimbled-enhancing-self-supervised-monocular","paper_url":"https://arxiv.org/abs/2408.14177v1","paper_title":"NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training","code":"https://github.com/xapaxca/nimbled","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"Nimbled-SwiftDepth","metrics":{"Delta < 1.25":"0.905","Delta < 1.25^2":"0.969","Delta < 1.25^3":"0.986","Mono":"O","RMSE":"4.333","RMSE log":"0.171","Resolution":"640x192","Sq Rel":"0.697","absolute relative error":"0.096"},"uses_additional_data":false,"paper_date":"2024-08-26","paper":"/paper/nimbled-enhancing-self-supervised-monocular","paper_url":"https://arxiv.org/abs/2408.14177v1","paper_title":"NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training","code":"https://github.com/xapaxca/nimbled","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"DynamicDepth (M+640x192)","metrics":{"Delta < 1.25":"0.897","Delta < 1.25^2":"0.964","Delta < 1.25^3":"0.984","Mono":"X","RMSE":"4.458","RMSE log":"0.175","Sq Rel":"0.720","absolute relative error":"0.096"},"uses_additional_data":false,"paper_date":"2022-03-29","paper":"/paper/disentangling-object-motion-and-occlusion-for","paper_url":"https://arxiv.org/abs/2203.15174v2","paper_title":"Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth","code":"https://github.com/AutoAILab/DynamicDepth","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":21,"model":"Nimbled-MD2-R50","metrics":{"Delta < 1.25":"0.904","Delta < 1.25^2":"0.968","Delta < 1.25^3":"0.985","Mono":"O","RMSE":"4.377","RMSE log":"0.172","Resolution":"640x192","Sq Rel":"0.721","absolute relative error":"0.097"},"uses_additional_data":false,"paper_date":"2024-08-26","paper":"/paper/nimbled-enhancing-self-supervised-monocular","paper_url":"https://arxiv.org/abs/2408.14177v1","paper_title":"NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training","code":"https://github.com/xapaxca/nimbled","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"SCIPaD(M+640x192)","metrics":{"Delta < 1.25":"0.897","Delta < 1.25^2":"0.964","Delta < 1.25^3":"0.983","Mono":"O","RMSE":"4.391","RMSE log":"0.175","Resolution":"640x192","Sq Rel":"0.732","absolute relative error":"0.098"},"uses_additional_data":false,"paper_date":"2024-07-07","paper":"/paper/scipad-incorporating-spatial-clues-into","paper_url":"https://arxiv.org/abs/2407.05283v1","paper_title":"SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning","code":"https://github.com/fengyi233/SCIPaD","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"Nimbled-SwiftDepth-S","metrics":{"Delta < 1.25":"0.901","Delta < 1.25^2":"0.968","Delta < 1.25^3":"0.985","Mono":"O","RMSE":"4.401","RMSE log":"0.174","Resolution":"640x192","Sq Rel":"0.733","absolute relative error":"0.098"},"uses_additional_data":false,"paper_date":"2024-08-26","paper":"/paper/nimbled-enhancing-self-supervised-monocular","paper_url":"https://arxiv.org/abs/2408.14177v1","paper_title":"NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training","code":"https://github.com/xapaxca/nimbled","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"CREMono(M + 1024x320 + Res50)","metrics":{"Delta < 1.25":"0.902","Delta < 1.25^2":" 0.969","Delta < 1.25^3":" 0.986","RMSE":"4.165","RMSE log":"0.171","Sq Rel":"0.624","absolute relative error":"0.099"},"uses_additional_data":false,"paper_date":"2022-10-23","paper":"/paper/towards-comprehensive-representation","paper_url":"https://link.springer.com/chapter/10.1007/978-3-031-19769-7_18","paper_title":"Towards Comprehensive Representation Enhancement in Semantics-guided Self-supervised Monocular Depth Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":25,"model":"NimbleD-LiteMono-S","metrics":{"Delta < 1.25":"0.898","Delta < 1.25^2":"0.967","Delta < 1.25^3":"0.986","Mono":"O","RMSE":"4.370","RMSE log":"0.172","Resolution":"640x192","Sq Rel":"0.709","absolute relative error":"0.099"},"uses_additional_data":false,"paper_date":"2024-08-26","paper":"/paper/nimbled-enhancing-self-supervised-monocular","paper_url":"https://arxiv.org/abs/2408.14177v1","paper_title":"NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training","code":"https://github.com/xapaxca/nimbled","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"FeatDepth-MS","metrics":{"Delta < 1.25":"0.889","Delta < 1.25^2":"0.963","Delta < 1.25^3":"0.982","RMSE":"4.427","RMSE log":"0.184","Sq Rel":"0.697","absolute relative error":"0.099"},"uses_additional_data":false,"paper_date":"2020-07-21","paper":"/paper/feature-metric-loss-for-self-supervised","paper_url":"https://arxiv.org/abs/2007.10603v1","paper_title":"Feature-metric Loss for Self-supervised Learning of Depth and Egomotion","code":"https://github.com/sconlyshootery/FeatDepth","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"VTDepthB2 (stereo supervision)","metrics":{"Delta < 1.25":"0.904","Delta < 1.25^2":"0.965","Delta < 1.25^3":"0.983","RMSE":"4.439","RMSE log":"0.178","Sq Rel":"0.743","absolute relative error":"0.099"},"uses_additional_data":false,"paper_date":"2022-12-27","paper":"/paper/exploring-efficiency-of-vision-transformers","paper_url":"https://ieeexplore.ieee.org/document/9995672","paper_title":"Exploring Efficiency of Vision Transformers for Self-Supervised Monocular Depth Estimation","code":"https://github.com/ahbpp/VTDepth","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"EPCDepth(S+640x192)","metrics":{"Delta < 1.25":"0.888","Delta < 1.25^2":"0.963","Delta < 1.25^3":"0.982","RMSE":"4.490","RMSE log":"0.183","Sq Rel":"0.754","absolute relative error":"0.099"},"uses_additional_data":false,"paper_date":"2021-09-26","paper":"/paper/excavating-the-potential-capacity-of-self","paper_url":"https://arxiv.org/abs/2109.12484v1","paper_title":"Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation","code":"https://github.com/prstrive/EPCDepth","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":29,"model":"Nimbled-MD2-R18","metrics":{"Delta < 1.25":"0.898","Delta < 1.25^2":"0.967","Delta < 1.25^3":"0.985","Mono":"O","RMSE":"4.440","RMSE log":"0.175","Resolution":"640x192","Sq Rel":"0.739","absolute relative error":"0.100"},"uses_additional_data":false,"paper_date":"2024-08-26","paper":"/paper/nimbled-enhancing-self-supervised-monocular","paper_url":"https://arxiv.org/abs/2408.14177v1","paper_title":"NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training","code":"https://github.com/xapaxca/nimbled","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"MonoDEVSNet","metrics":{"Delta < 1.25":"0.882","Delta < 1.25^2":"0.962","RMSE":"4.413","Sq Rel":"0.703","absolute relative error":"0.101"},"uses_additional_data":false,"paper_date":"2021-03-22","paper":"/paper/monocular-depth-estimation-through-virtual","paper_url":"https://arxiv.org/abs/2103.12209v3","paper_title":"Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision","code":"https://github.com/HMRC-AEL/MonoDEVSNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"HR-Depth-MS-1024X320","metrics":{"absolute relative error":"0.101"},"uses_additional_data":false,"paper_date":"2020-12-14","paper":"/paper/hr-depth-high-resolution-self-supervised","paper_url":"https://arxiv.org/abs/2012.07356v1","paper_title":"HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation","code":"https://github.com/shawLyu/HR-Depth","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"X-Distill (M+1024x320)","metrics":{"Delta < 1.25":"0.895","Delta < 1.25^2":"0.965","Delta < 1.25^3":"0.983","RMSE":"4.439","RMSE log":"0.180","Sq Rel":"0.698","absolute relative error":"0.102"},"uses_additional_data":false,"paper_date":"2021-10-24","paper":"/paper/x-distill-improving-self-supervised-monocular","paper_url":"https://arxiv.org/abs/2110.12516v1","paper_title":"X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":33,"model":"CamLessMonoDepth-1024x320","metrics":{"absolute relative error":"0.102"},"uses_additional_data":false,"paper_date":"2021-10-27","paper":"/paper/camlessmonodepth-monocular-depth-estimation","paper_url":"https://arxiv.org/abs/2110.14347v1","paper_title":"CamLessMonoDepth: Monocular Depth Estimation with Unknown Camera Parameters","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":34,"model":"GCNDepth","metrics":{"RMSE":"4.494","RMSE log":"0.181","Sq Rel":"0.720","absolute relative error":"0.104"},"uses_additional_data":false,"paper_date":"2021-12-13","paper":"/paper/gcndepth-self-supervised-monocular-depth","paper_url":"https://arxiv.org/abs/2112.06782v1","paper_title":"GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional Network","code":"https://github.com/arminmasoumian/gcndepth","n_code_links":1,"syntology":null},{"rank_in_archive_order":35,"model":"FeatDepth-M","metrics":{"absolute relative error":"0.104"},"uses_additional_data":false,"paper_date":"2020-07-21","paper":"/paper/feature-metric-loss-for-self-supervised","paper_url":"https://arxiv.org/abs/2007.10603v1","paper_title":"Feature-metric Loss for Self-supervised Learning of Depth and Egomotion","code":"https://github.com/sconlyshootery/FeatDepth","n_code_links":1,"syntology":null},{"rank_in_archive_order":36,"model":"HR-Depth-M-1280x384","metrics":{"absolute relative error":"0.104"},"uses_additional_data":false,"paper_date":"2020-12-14","paper":"/paper/hr-depth-high-resolution-self-supervised","paper_url":"https://arxiv.org/abs/2012.07356v1","paper_title":"HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation","code":"https://github.com/shawLyu/HR-Depth","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":37,"model":"Lite-HR-Depth-T-1280x384","metrics":{"absolute relative error":"0.104"},"uses_additional_data":false,"paper_date":"2020-12-14","paper":"/paper/hr-depth-high-resolution-self-supervised","paper_url":"https://arxiv.org/abs/2012.07356v1","paper_title":"HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation","code":"https://github.com/shawLyu/HR-Depth","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":38,"model":"MonoFormer","metrics":{"Mono":"O","Resolution":"640x192","absolute relative error":"0.104"},"uses_additional_data":false,"paper_date":"2022-05-23","paper":"/paper/monoformer-towards-generalization-of-self","paper_url":"https://arxiv.org/abs/2205.11083v3","paper_title":"Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation","code":"https://github.com/sjg02122/MonoFormer","n_code_links":1,"syntology":null},{"rank_in_archive_order":39,"model":"VTDepthB2 (monocular supervision)","metrics":{"Delta < 1.25":"0.893","Delta < 1.25^2":"0.964","Delta < 1.25^3":"0.983","RMSE":"4.530","RMSE log":"0.182","Sq Rel":"0.762","absolute relative error":"0.105"},"uses_additional_data":false,"paper_date":"2022-12-27","paper":"/paper/exploring-efficiency-of-vision-transformers","paper_url":"https://ieeexplore.ieee.org/document/9995672","paper_title":"Exploring Efficiency of Vision Transformers for Self-Supervised Monocular Depth Estimation","code":"https://github.com/ahbpp/VTDepth","n_code_links":1,"syntology":null},{"rank_in_archive_order":40,"model":"CamLessMonoDepth (V1)-640x192","metrics":{"absolute relative error":"0.105"},"uses_additional_data":false,"paper_date":"2021-10-27","paper":"/paper/camlessmonodepth-monocular-depth-estimation","paper_url":"https://arxiv.org/abs/2110.14347v1","paper_title":"CamLessMonoDepth: Monocular Depth Estimation with Unknown Camera Parameters","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":41,"model":"Monodepth2 MS","metrics":{"absolute relative error":"0.106"},"uses_additional_data":false,"paper_date":"2019-10-01","paper":"/paper/digging-into-self-supervised-monocular-depth-1","paper_url":"http://openaccess.thecvf.com/content_ICCV_2019/html/Godard_Digging_Into_Self-Supervised_Monocular_Depth_Estimation_ICCV_2019_paper.html","paper_title":"Digging Into Self-Supervised Monocular Depth Estimation","code":"https://github.com/nianticlabs/monodepth2","n_code_links":3,"syntology":null},{"rank_in_archive_order":42,"model":"CamLessMonoDepth (V2)-640x192","metrics":{"absolute relative error":"0.106"},"uses_additional_data":false,"paper_date":"2021-10-27","paper":"/paper/camlessmonodepth-monocular-depth-estimation","paper_url":"https://arxiv.org/abs/2110.14347v1","paper_title":"CamLessMonoDepth: Monocular Depth Estimation with Unknown Camera Parameters","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":43,"model":"PackNet-SfM M","metrics":{"absolute relative error":"0.107"},"uses_additional_data":false,"paper_date":"2019-05-06","paper":"/paper/packnet-sfm-3d-packing-for-self-supervised","paper_url":"https://arxiv.org/abs/1905.02693v4","paper_title":"3D Packing for Self-Supervised Monocular Depth Estimation","code":"https://github.com/TRI-ML/packnet-sfm","n_code_links":4,"syntology":null},{"rank_in_archive_order":44,"model":"SharinGAN","metrics":{"Delta < 1.25":"0.864","Delta < 1.25^2":"0.954","Delta < 1.25^3":"0.981","RMSE":"3.77","RMSE log":"0.19","Sq Rel":"0.673","absolute relative error":"0.109"},"uses_additional_data":false,"paper_date":"2020-06-07","paper":"/paper/sharingan-combining-synthetic-and-real-data-1","paper_url":"https://arxiv.org/abs/2006.04026v1","paper_title":"SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation","code":"https://github.com/koutilya40192/SharinGAN","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"DCPI-Depth (M+832x256+SC-V3)","metrics":{"RMSE":"4.496","Sq Rel":"0.679","absolute relative error":"0.109"},"uses_additional_data":false,"paper_date":"2024-05-27","paper":"/paper/dcpi-depth-explicitly-infusing-dense","paper_url":"https://arxiv.org/abs/2405.16960v2","paper_title":"DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":46,"model":"Monodepth2 S","metrics":{"absolute relative error":"0.109"},"uses_additional_data":false,"paper_date":"2019-10-01","paper":"/paper/digging-into-self-supervised-monocular-depth-1","paper_url":"http://openaccess.thecvf.com/content_ICCV_2019/html/Godard_Digging_Into_Self-Supervised_Monocular_Depth_Estimation_ICCV_2019_paper.html","paper_title":"Digging Into Self-Supervised Monocular Depth Estimation","code":"https://github.com/nianticlabs/monodepth2","n_code_links":3,"syntology":null},{"rank_in_archive_order":47,"model":"HR-Depth-M-640x192","metrics":{"absolute relative error":"0.109"},"uses_additional_data":false,"paper_date":"2020-12-14","paper":"/paper/hr-depth-high-resolution-self-supervised","paper_url":"https://arxiv.org/abs/2012.07356v1","paper_title":"HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation","code":"https://github.com/shawLyu/HR-Depth","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":48,"model":"G2S (MD2-M-R18-pp-640 x 192)","metrics":{"absolute relative error":"0.109"},"uses_additional_data":false,"paper_date":"2021-03-03","paper":"/paper/multimodal-scale-consistency-and-awareness","paper_url":"https://arxiv.org/abs/2103.02451v1","paper_title":"Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimation","code":"https://github.com/NeurAI-Lab/G2S","n_code_links":1,"syntology":null},{"rank_in_archive_order":49,"model":"SuperDepth S","metrics":{"absolute relative error":"0.112"},"uses_additional_data":false,"paper_date":"2018-10-03","paper":"/paper/superdepth-self-supervised-super-resolved","paper_url":"http://arxiv.org/abs/1810.01849v1","paper_title":"SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":50,"model":"Occlusion_mask_640x192","metrics":{"absolute relative error":"0.113"},"uses_additional_data":false,"paper_date":"2019-08-29","paper":"/paper/improving-self-supervised-single-view-depth","paper_url":"https://arxiv.org/abs/1908.11112v1","paper_title":"Improving Self-Supervised Single View Depth Estimation by Masking Occlusion","code":"https://github.com/schelv/monodepth2","n_code_links":1,"syntology":null},{"rank_in_archive_order":51,"model":"pc4consistentdepth","metrics":{"absolute relative error":"0.113"},"uses_additional_data":false,"paper_date":"2023-04-18","paper":"/paper/pose-constraints-for-consistent-self","paper_url":"https://arxiv.org/abs/2304.08916v1","paper_title":"Pose Constraints for Consistent Self-supervised Monocular Depth and Ego-motion","code":"https://github.com/zshn25/pc4consistentdepth","n_code_links":1,"syntology":null},{"rank_in_archive_order":52,"model":"Dyna-DM","metrics":{"Delta < 1.25":"0.871","Delta < 1.25^2":"0.959","Delta < 1.25^3":"0.982","RMSE":"4.698","RMSE log":"0.192","Sq Rel":"0.785","absolute relative error":"0.115"},"uses_additional_data":false,"paper_date":"2022-06-08","paper":"/paper/dyna-dm-dynamic-object-aware-self-supervised","paper_url":"https://arxiv.org/abs/2206.03799v3","paper_title":"Dyna-DM: Dynamic Object-aware Self-supervised Monocular Depth Maps","code":"https://github.com/kieran514/dyna-dm","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":53,"model":"Monodepth2 M","metrics":{"Test frames":"1","absolute relative error":"0.115"},"uses_additional_data":false,"paper_date":"2019-10-01","paper":"/paper/digging-into-self-supervised-monocular-depth-1","paper_url":"http://openaccess.thecvf.com/content_ICCV_2019/html/Godard_Digging_Into_Self-Supervised_Monocular_Depth_Estimation_ICCV_2019_paper.html","paper_title":"Digging Into Self-Supervised Monocular Depth Estimation","code":"https://github.com/nianticlabs/monodepth2","n_code_links":3,"syntology":null},{"rank_in_archive_order":54,"model":"Monodepth S","metrics":{"absolute relative error":"0.133"},"uses_additional_data":false,"paper_date":"2016-09-13","paper":"/paper/unsupervised-monocular-depth-estimation-with","paper_url":"http://arxiv.org/abs/1609.03677v3","paper_title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","code":"https://github.com/mrharicot/monodepth","n_code_links":16,"syntology":{"n_ran":3,"n_unverified":9,"n_samples":12,"n_pointer_only_licence":5}},{"rank_in_archive_order":55,"model":"Struct2Depth M","metrics":{"absolute relative error":"0.1412"},"uses_additional_data":false,"paper_date":"2019-06-12","paper":"/paper/unsupervised-monocular-depth-and-ego-motion","paper_url":"https://arxiv.org/abs/1906.05717v1","paper_title":"Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semantics","code":null,"n_code_links":0,"syntology":null}],"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 6,795 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":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"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":14,"rows_with_any_sample_ran":12,"distinct_papers_with_graph_line":9,"distinct_papers_with_any_sample_ran":8,"samples_over_distinct_papers":{"n_ran":29,"n_unverified":21,"n_samples":50,"n_pointer_only_licence":11,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":33,"n_unverified":31,"n_samples":64,"n_pointer_only_licence":11,"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"}}}