{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/depth-estimation/papers/12","list_of":"/task/depth-estimation","task":"Depth Estimation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":12,"pages_in_order":25,"rows_per_page":100,"rows":[1101,1200],"of":2454,"counts":{"archive_papers_tagged":2454,"with_a_code_link":1029,"where_syntology_ran_a_sample":292,"not_listed_spam_title":0,"listed":2454,"listed_where_code_ran":292,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":260,"every_run_a_failure_of_syntologys_instrument":32,"listed_with_a_run_with_no_instrument_failure":260,"listed_every_run_a_failure_of_syntologys_instrument":32,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/depth-estimation","prev":"/task/depth-estimation/papers/11","next":"/task/depth-estimation/papers/13","papers":[{"url":null,"slug":"deepwheel-generating-a-3d-synthetic-wheel","title":"DeepWheel: Generating a 3D Synthetic Wheel Dataset for Design and Performance Evaluation","date":"2025-04-15","arxiv_id":"2504.11347","repositories_listed":0,"syntology":null},{"url":null,"slug":"endo3r-unified-online-reconstruction-from","title":"Endo3R: Unified Online Reconstruction from Dynamic Monocular Endoscopic Video","date":"2025-04-04","arxiv_id":"2504.03198","repositories_listed":0,"syntology":null},{"url":null,"slug":"ringmoe-mixture-of-modality-experts-multi","title":"RingMoE: Mixture-of-Modality-Experts Multi-Modal Foundation Models for Universal Remote Sensing Image Interpretation","date":"2025-04-04","arxiv_id":"2504.03166","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-gesture-interaction-control-method","title":"A novel gesture interaction control method for rehabilitation lower extremity exoskeleton","date":"2025-04-02","arxiv_id":"2504.01888","repositories_listed":0,"syntology":null},{"url":null,"slug":"fresca-unveiling-the-scaling-space-in","title":"FreSca: Unveiling the Scaling Space in Diffusion Models","date":"2025-04-02","arxiv_id":"2504.02154","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaussianlss-toward-real-world-bev-perception","title":"GaussianLSS -- Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting","date":"2025-04-02","arxiv_id":"2504.01957","repositories_listed":0,"syntology":null},{"url":null,"slug":"geometrycrafter-consistent-geometry","title":"GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors","date":"2025-04-01","arxiv_id":"2504.01016","repositories_listed":0,"syntology":null},{"url":null,"slug":"monocular-and-generalizable-gaussian-talking","title":"Monocular and Generalizable Gaussian Talking Head Animation","date":"2025-04-01","arxiv_id":"2504.00665","repositories_listed":0,"syntology":null},{"url":null,"slug":"detail-aware-multi-view-stereo-network-for","title":"Detail-aware multi-view stereo network for depth estimation","date":"2025-03-31","arxiv_id":"2503.23684","repositories_listed":0,"syntology":null},{"url":null,"slug":"exscene-free-view-3d-scene-reconstruction","title":"ExScene: Free-View 3D Scene Reconstruction with Gaussian Splatting from a Single Image","date":"2025-03-31","arxiv_id":"2503.23881","repositories_listed":0,"syntology":null},{"url":null,"slug":"blurry-edges-photon-limited-depth-estimation","title":"Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries","date":"2025-03-30","arxiv_id":"2503.23606","repositories_listed":0,"syntology":null},{"url":null,"slug":"intrinsic-image-decomposition-for-robust-self","title":"Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces","date":"2025-03-28","arxiv_id":"2503.22209","repositories_listed":0,"syntology":null},{"url":null,"slug":"mvsanywhere-zero-shot-multi-view-stereo","title":"MVSAnywhere: Zero-Shot Multi-View Stereo","date":"2025-03-28","arxiv_id":"2503.22430","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-look-is-enough-a-novel-seamless-patchwise","title":"One Look is Enough: A Novel Seamless Patchwise Refinement for Zero-Shot Monocular Depth Estimation Models on High-Resolution Images","date":"2025-03-28","arxiv_id":"2503.22351","repositories_listed":0,"syntology":null},{"url":null,"slug":"icg-mvsnet-learning-intra-view-and-cross-view","title":"ICG-MVSNet: Learning Intra-view and Cross-view Relationships for Guidance in Multi-View Stereo","date":"2025-03-27","arxiv_id":"2503.21525","repositories_listed":0,"syntology":null},{"url":null,"slug":"omnidirectional-depth-aided-occupancy","title":"Omnidirectional Depth-Aided Occupancy Prediction based on Cylindrical Voxel for Autonomous Driving","date":"2025-03-26","arxiv_id":"2504.01023","repositories_listed":0,"syntology":null},{"url":null,"slug":"tracktention-leveraging-point-tracking-to","title":"Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better","date":"2025-03-25","arxiv_id":"2503.19904","repositories_listed":0,"syntology":null},{"url":null,"slug":"pddm-pseudo-depth-diffusion-model-for-rgb-pd","title":"PDDM: Pseudo Depth Diffusion Model for RGB-PD Semantic Segmentation Based in Complex Indoor Scenes","date":"2025-03-24","arxiv_id":"2503.18393","repositories_listed":0,"syntology":null},{"url":null,"slug":"stablegs-a-floater-free-framework-for-3d","title":"StableGS: A Floater-Free Framework for 3D Gaussian Splatting","date":"2025-03-24","arxiv_id":"2503.18458","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaa-tso-geometry-aware-assisted-depth","title":"GAA-TSO: Geometry-Aware Assisted Depth Completion for Transparent and Specular Objects","date":"2025-03-21","arxiv_id":"2503.17106","repositories_listed":0,"syntology":null},{"url":null,"slug":"pow3r-empowering-unconstrained-3d","title":"Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors","date":"2025-03-21","arxiv_id":"2503.17316","repositories_listed":0,"syntology":null},{"url":null,"slug":"radar-guided-polynomial-fitting-for-metric","title":"Radar-Guided Polynomial Fitting for Metric Depth Estimation","date":"2025-03-21","arxiv_id":"2503.17182","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-point-maps-a-versatile-representation","title":"Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction","date":"2025-03-20","arxiv_id":"2503.16318","repositories_listed":0,"syntology":null},{"url":"/paper/jasmine-harnessing-diffusion-prior-for-self","slug":"jasmine-harnessing-diffusion-prior-for-self","title":"Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation","date":"2025-03-20","arxiv_id":"2503.15905","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-efficiently-adapt-foundation","title":"Learning to Efficiently Adapt Foundation Models for Self-Supervised Endoscopic 3D Scene Reconstruction from Any Cameras","date":"2025-03-20","arxiv_id":"2503.15917","repositories_listed":0,"syntology":null},{"url":null,"slug":"tulip-towards-unified-language-image","title":"TULIP: Towards Unified Language-Image Pretraining","date":"2025-03-19","arxiv_id":"2503.15485","repositories_listed":0,"syntology":null},{"url":null,"slug":"usam-net-a-u-net-based-network-for-improved","title":"USAM-Net: A U-Net-based Network for Improved Stereo Correspondence and Scene Depth Estimation using Features from a Pre-trained Image Segmentation network","date":"2025-03-19","arxiv_id":"2503.14950","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-densification-for-multi-map-monocular","title":"3D Densification for Multi-Map Monocular VSLAM in Endoscopy","date":"2025-03-18","arxiv_id":"2503.14346","repositories_listed":0,"syntology":null},{"url":null,"slug":"dune-distilling-a-universal-encoder-from","title":"DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers","date":"2025-03-18","arxiv_id":"2503.14405","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-view-reconstruction-via-sfm-guided","title":"Multi-view Reconstruction via SfM-guided Monocular Depth Estimation","date":"2025-03-18","arxiv_id":"2503.14483","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-geometric-consistency-for-360","title":"Improving Geometric Consistency for 360-Degree Neural Radiance Fields in Indoor Scenarios","date":"2025-03-17","arxiv_id":"2503.13710","repositories_listed":0,"syntology":null},{"url":null,"slug":"monoct-overcoming-monocular-3d-detection","title":"MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models","date":"2025-03-17","arxiv_id":"2503.13743","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-and-seeing-through-the-glass-real-and","title":"Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation","date":"2025-03-14","arxiv_id":"2503.11633","repositories_listed":0,"syntology":null},{"url":null,"slug":"flow-nerf-joint-learning-of-geometry-poses","title":"Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations","date":"2025-03-13","arxiv_id":"2503.10464","repositories_listed":0,"syntology":null},{"url":null,"slug":"wonderverse-extendable-3d-scene-generation","title":"WonderVerse: Extendable 3D Scene Generation with Video Generative Models","date":"2025-03-12","arxiv_id":"2503.09160","repositories_listed":0,"syntology":null},{"url":null,"slug":"garmentcrafter-progressive-novel-view","title":"GarmentCrafter: Progressive Novel View Synthesis for Single-View 3D Garment Reconstruction and Editing","date":"2025-03-11","arxiv_id":"2503.08678","repositories_listed":0,"syntology":null},{"url":null,"slug":"endo-fast3r-endoscopic-foundation-model","title":"Endo-FASt3r: Endoscopic Foundation model Adaptation for Structure from motion","date":"2025-03-10","arxiv_id":"2503.07204","repositories_listed":0,"syntology":null},{"url":null,"slug":"evidmtl-evidential-multi-task-learning-for","title":"EvidMTL: Evidential Multi-Task Learning for Uncertainty-Aware Semantic Surface Mapping from Monocular RGB Images","date":"2025-03-06","arxiv_id":"2503.04441","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-view-depth-consistent-image-generation","title":"Multi-View Depth Consistent Image Generation Using Generative AI Models: Application on Architectural Design of University Buildings","date":"2025-03-05","arxiv_id":"2503.03068","repositories_listed":0,"syntology":null},{"url":null,"slug":"rtfusion-a-depth-estimation-network-based-on","title":"RGB-Thermal Infrared Fusion for Robust Depth Estimation in Complex Environments","date":"2025-03-05","arxiv_id":"2503.04821","repositories_listed":0,"syntology":null},{"url":null,"slug":"slam-in-the-dark-self-supervised-learning-of","title":"SLAM in the Dark: Self-Supervised Learning of Pose, Depth and Loop-Closure from Thermal Images","date":"2025-02-26","arxiv_id":"2502.18932","repositories_listed":0,"syntology":null},{"url":null,"slug":"rgb-only-gaussian-splatting-slam-for","title":"RGB-Only Gaussian Splatting SLAM for Unbounded Outdoor Scenes","date":"2025-02-21","arxiv_id":"2502.15633","repositories_listed":0,"syntology":null},{"url":null,"slug":"lxlv2-enhanced-lidar-excluded-lean-3d-object","title":"LXLv2: Enhanced LiDAR Excluded Lean 3D Object Detection with Fusion of 4D Radar and Camera","date":"2025-02-20","arxiv_id":"2502.14503","repositories_listed":0,"syntology":null},{"url":null,"slug":"orcharddepth-precise-metric-depth-estimation","title":"OrchardDepth: Precise Metric Depth Estimation of Orchard Scene from Monocular Camera Images","date":"2025-02-20","arxiv_id":"2502.14279","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-monocular-depth-estimation-7","title":"Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet Mining","date":"2025-02-20","arxiv_id":"2502.14573","repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-training-auto-regressive-robotic-models","title":"Pre-training Auto-regressive Robotic Models with 4D Representations","date":"2025-02-18","arxiv_id":"2502.13142","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-neural-networks-for-accurate-depth","title":"Deep Neural Networks for Accurate Depth Estimation with Latent Space Features","date":"2025-02-17","arxiv_id":"2502.11777","repositories_listed":0,"syntology":null},{"url":null,"slug":"adjust-your-focus-defocus-deblurring-from","title":"Adjust Your Focus: Defocus Deblurring From Dual-Pixel Images Using Explicit Multi-Scale Cross-Correlation","date":"2025-02-16","arxiv_id":"2502.11002","repositories_listed":0,"syntology":null},{"url":null,"slug":"realcam-i2v-real-world-image-to-video","title":"RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control","date":"2025-02-14","arxiv_id":"2502.10059","repositories_listed":0,"syntology":null},{"url":null,"slug":"col3d-collaborative-learning-of-single-view","title":"CoL3D: Collaborative Learning of Single-view Depth and Camera Intrinsics for Metric 3D Shape Recovery","date":"2025-02-13","arxiv_id":"2502.08902","repositories_listed":0,"syntology":null},{"url":null,"slug":"s-2-diffusion-generalizing-from-instance","title":"S$^2$-Diffusion: Generalizing from Instance-level to Category-level Skills in Robot Manipulation","date":"2025-02-13","arxiv_id":"2502.09389","repositories_listed":0,"syntology":null},{"url":null,"slug":"steroi-d-system-design-and-mapping-for-stereo","title":"SteROI-D: System Design and Mapping for Stereo Depth Inference on Regions of Interest","date":"2025-02-13","arxiv_id":"2502.09528","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-inverse-laplacian-pyramid-for","title":"Learning Inverse Laplacian Pyramid for Progressive Depth Completion","date":"2025-02-11","arxiv_id":"2502.07289","repositories_listed":0,"syntology":null},{"url":null,"slug":"matrix3d-large-photogrammetry-model-all-in","title":"Matrix3D: Large Photogrammetry Model All-in-One","date":"2025-02-11","arxiv_id":"2502.07685","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-image-to-video-an-empirical-study-of","title":"From Image to Video: An Empirical Study of Diffusion Representations","date":"2025-02-10","arxiv_id":"2502.07001","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-exploiting-vision-foundation-model-s","title":"Fully Exploiting Vision Foundation Model's Profound Prior Knowledge for Generalizable RGB-Depth Driving Scene Parsing","date":"2025-02-10","arxiv_id":"2502.06219","repositories_listed":0,"syntology":null},{"url":null,"slug":"spherefusion-efficient-panorama-depth","title":"SphereFusion: Efficient Panorama Depth Estimation via Gated Fusion","date":"2025-02-09","arxiv_id":"2502.05859","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-rome-with-convex-optimization","title":"Building Rome with Convex Optimization","date":"2025-02-07","arxiv_id":"2502.04640","repositories_listed":0,"syntology":null},{"url":null,"slug":"metafe-de-learning-meta-feature-embedding-for","title":"MetaFE-DE: Learning Meta Feature Embedding for Depth Estimation from Monocular Endoscopic Images","date":"2025-02-05","arxiv_id":"2502.03493","repositories_listed":0,"syntology":null},{"url":null,"slug":"doc-depth-a-novel-approach-for-dense-depth","title":"DOC-Depth: A novel approach for dense depth ground truth generation","date":"2025-02-04","arxiv_id":"2502.02144","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-stable-diffusion-for-monocular","title":"Leveraging Stable Diffusion for Monocular Depth Estimation via Image Semantic Encoding","date":"2025-02-01","arxiv_id":"2502.01666","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-novel-view-and-depth-synthesis-with","title":"Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion","date":"2025-01-30","arxiv_id":"2501.18804","repositories_listed":0,"syntology":null},{"url":null,"slug":"snapshot-compressed-imaging-based-single","title":"Snapshot Compressed Imaging Based Single-Measurement Computer Vision for Videos","date":"2025-01-25","arxiv_id":"2501.15122","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-encoder-decoder-flow-through","title":"Rethinking Encoder-Decoder Flow Through Shared Structures","date":"2025-01-24","arxiv_id":"2501.14535","repositories_listed":0,"syntology":null},{"url":null,"slug":"imagine-e-image-generation-intelligence","title":"IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models","date":"2025-01-23","arxiv_id":"2501.13920","repositories_listed":0,"syntology":null},{"url":null,"slug":"promptmono-cross-prompting-attention-for-self","title":"PromptMono: Cross Prompting Attention for Self-Supervised Monocular Depth Estimation in Challenging Environments","date":"2025-01-23","arxiv_id":"2501.13796","repositories_listed":0,"syntology":null},{"url":null,"slug":"uniuir-considering-underwater-image","title":"UniUIR: Considering Underwater Image Restoration as An All-in-One Learner","date":"2025-01-22","arxiv_id":"2501.12981","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-underwater-scene-reconstruction-using","title":"Fast Underwater Scene Reconstruction using Multi-View Stereo and Physical Imaging","date":"2025-01-21","arxiv_id":"2501.11884","repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-on-monocular-metric-depth-estimation","title":"Survey on Monocular Metric Depth Estimation","date":"2025-01-21","arxiv_id":"2501.11841","repositories_listed":0,"syntology":null},{"url":null,"slug":"rdg-gs-relative-depth-guidance-with-gaussian","title":"RDG-GS: Relative Depth Guidance with Gaussian Splatting for Real-time Sparse-View 3D Rendering","date":"2025-01-19","arxiv_id":"2501.11102","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-d-piece-image-tokenizer-meets-quality","title":"One-D-Piece: Image Tokenizer Meets Quality-Controllable Compression","date":"2025-01-17","arxiv_id":"2501.10064","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-monocular-scene-flow-estimation-in","title":"Zero-Shot Monocular Scene Flow Estimation in the Wild","date":"2025-01-17","arxiv_id":"2501.10357","repositories_listed":0,"syntology":null},{"url":null,"slug":"stereogen-high-quality-stereo-image","title":"StereoGen: High-quality Stereo Image Generation from a Single Image","date":"2025-01-15","arxiv_id":"2501.08654","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-critical-synthesis-of-uncertainty","title":"A Critical Synthesis of Uncertainty Quantification and Foundation Models in Monocular Depth Estimation","date":"2025-01-14","arxiv_id":"2501.08188","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-birds-eye-view-perception-models","title":"Revisiting Birds Eye View Perception Models with Frozen Foundation Models: DINOv2 and Metric3Dv2","date":"2025-01-14","arxiv_id":"2501.08118","repositories_listed":0,"syntology":null},{"url":null,"slug":"matching-free-depth-recovery-from-structured","title":"Matching Free Depth Recovery from Structured Light","date":"2025-01-13","arxiv_id":"2501.07113","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-systematic-literature-review-on-deep","title":"A Systematic Literature Review on Deep Learning-based Depth Estimation in Computer Vision","date":"2025-01-09","arxiv_id":"2501.05147","repositories_listed":0,"syntology":null},{"url":null,"slug":"igaf-incremental-guided-attention-fusion-for","title":"IGAF: Incremental Guided Attention Fusion for Depth Super-Resolution","date":"2025-01-03","arxiv_id":"2501.01723","repositories_listed":0,"syntology":null},{"url":null,"slug":"laparoscopic-scene-analysis-for","title":"Laparoscopic Scene Analysis for Intraoperative Visualisation of Gamma Probe Signals in Minimally Invasive Cancer Surgery","date":"2025-01-03","arxiv_id":"2501.01752","repositories_listed":0,"syntology":null},{"url":null,"slug":"safeaug-safety-critical-driving-data","title":"SafeAug: Safety-Critical Driving Data Augmentation from Naturalistic Datasets","date":"2025-01-03","arxiv_id":"2501.02143","repositories_listed":0,"syntology":null},{"url":null,"slug":"patchrefiner-v2-fast-and-lightweight-real","title":"PatchRefiner V2: Fast and Lightweight Real-Domain High-Resolution Metric Depth Estimation","date":"2025-01-02","arxiv_id":"2501.01121","repositories_listed":0,"syntology":null},{"url":null,"slug":"texavi-generating-stereoscopic-vr-video-clips","title":"TexAVi: Generating Stereoscopic VR Video Clips from Text Descriptions","date":"2025-01-02","arxiv_id":"2501.01156","repositories_listed":0,"syntology":null},{"url":null,"slug":"asynchronous-collaborative-graph","title":"Asynchronous Collaborative Graph Representation for Frames and Events","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"blade-single-view-body-mesh-estimation","title":"BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ch3depth-efficient-and-flexible-depth","title":"CH3Depth: Efficient and Flexible Depth Foundation Model with Flow Matching","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-monocular-foundation-model-for","title":"Distilling Monocular Foundation Model for Fine-grained Depth Completion","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"flowing-from-words-to-pixels-a-noise-free","title":"Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"geodepth-from-point-to-depth-to-plane-to","title":"GeoDepth: From Point-to-Depth to Plane-to-Depth Modeling for Self-Supervised Monocular Depth Estimation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hush-holistic-panoramic-3d-scene","title":"HUSH: Holistic Panoramic 3D Scene Understanding using Spherical Harmonics","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-monocular-depth-prediction-using","title":"Improved Monocular Depth Prediction Using Distance Transform Over Pre-semantic Contours with Self-supervised Neural Networks","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-optimization-of-neural-radiance-fields","title":"Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learned-binocular-encoding-optics-for-rgbd","title":"Learned Binocular-Encoding Optics for RGBD Imaging Using Joint Stereo and Focus Cues","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"megasam-accurate-fast-and-robust-structure-1","title":"MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"panda-towards-panoramic-depth-anything-with","title":"PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"perceptual-inductive-bias-is-what-you-need","title":"Perceptual Inductive Bias Is What You Need Before Contrastive Learning","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rectification-specific-supervision-and","title":"Rectification-specific Supervision and Constrained Estimator for Online Stereo Rectification","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sdgocc-semantic-and-depth-guided-bird-s-eye","title":"SDGOCC: Semantic and Depth-Guided Bird's-Eye View Transformation for 3D Multimodal Occupancy Prediction","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-real-world-bev-perception-depth","title":"Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-embodiment-for-monocular","title":"Vision-Language Embodiment for Monocular Depth Estimation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tech-report-divide-and-conquer-3d-real-time","title":"Tech Report: Divide and Conquer 3D Real-Time Reconstruction for Improved IGS","date":"2024-12-31","arxiv_id":"2501.01465","repositories_listed":0,"syntology":null}],"record_sha256":"70f3b915c3563696126b1ceebace1547fe3185e31754a5d42fd837e3c4250d6a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}