{"url":"/task/stereo-depth-estimation","name":"Stereo Depth Estimation","slug":"stereo-depth-estimation","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":97,"papers_with_code":55,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":6,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/stereo-depth-estimation-on-kitti2015","slug":"stereo-depth-estimation-on-kitti2015","dataset":"KITTI2015","dataset_url":"/dataset/kitti","rows_in_archive":7,"metrics":[" three pixel error","three pixel error","D1-all All","D1-all Noc"],"first_row_in_archive_order":{"model":"AnyNet","paper_title":"Anytime Stereo Image Depth Estimation on Mobile Devices","paper_url":"/paper/anytime-stereo-image-depth-estimation-on","paper_date":"2018-10-26","arxiv_id":"1810.11408","code_links":[{"title":"mileyan/AnyNet","url":"https://github.com/mileyan/AnyNet"},{"title":"mamoanwar97/Anynet_modified","url":"https://github.com/mamoanwar97/Anynet_modified"},{"title":"rajeevpatwari/anynet","url":"https://github.com/rajeevpatwari/anynet"}],"syntology":{"n":26,"n_ran":3,"n_unverified":23,"n_pointer_only":0}}},{"leaderboard":"/sota/stereo-depth-estimation-on-spring","slug":"stereo-depth-estimation-on-spring","dataset":"Spring","dataset_url":"/dataset/spring","rows_in_archive":4,"metrics":["1px total"],"first_row_in_archive_order":{"model":"ACVNet","paper_title":"Attention Concatenation Volume for Accurate and Efficient Stereo Matching","paper_url":"/paper/acvnet-attention-concatenation-volume-for","paper_date":"2022-03-04","arxiv_id":"2203.02146","code_links":[{"title":"gangweix/acvnet","url":"https://github.com/gangweix/acvnet"},{"title":"ibaiGorordo/ONNX-ACVNet-Stereo-Depth-Estimation","url":"https://github.com/ibaiGorordo/ONNX-ACVNet-Stereo-Depth-Estimation"}],"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/stereo-depth-estimation-on-sceneflow","slug":"stereo-depth-estimation-on-sceneflow","dataset":"sceneflow","dataset_url":null,"rows_in_archive":3,"metrics":["Average End-Point Error","EPE"],"first_row_in_archive_order":{"model":"3D-MobileStereoNet","paper_title":"MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching","paper_url":"/paper/mobilestereonet-towards-lightweight-deep","paper_date":"2021-08-22","arxiv_id":"2108.09770","code_links":[{"title":"cogsys-tuebingen/mobilestereonet","url":"https://github.com/cogsys-tuebingen/mobilestereonet"},{"title":"ibaiGorordo/ONNX-MobileStereoNet","url":"https://github.com/ibaiGorordo/ONNX-MobileStereoNet"},{"title":"UCI-ISA-Lab/MultiHeadDepth-HomoDepth","url":"https://github.com/UCI-ISA-Lab/MultiHeadDepth-HomoDepth"},{"title":"ibaiGorordo/TFLite-MobileStereoNet","url":"https://github.com/ibaiGorordo/TFLite-MobileStereoNet"}],"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/stereo-depth-estimation-on-kitti-2015","slug":"stereo-depth-estimation-on-kitti-2015","dataset":"KITTI 2015","dataset_url":"/dataset/kitti","rows_in_archive":2,"metrics":["D1-all All","D1-all Noc"],"first_row_in_archive_order":{"model":"MoCha-Stereo","paper_title":"MoCha-Stereo: Motif Channel Attention Network for Stereo Matching","paper_url":"/paper/mocha-stereo-motif-channel-attention-network","paper_date":"2024-04-10","arxiv_id":"2404.06842","code_links":[{"title":"zyangchen/mocha-stereo","url":"https://github.com/zyangchen/mocha-stereo"}],"syntology":{"n":17,"n_ran":16,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/stereo-depth-estimation-on-kitti2012","slug":"stereo-depth-estimation-on-kitti2012","dataset":"KITTI2012","dataset_url":"/dataset/kitti","rows_in_archive":1,"metrics":[" three pixel error"],"first_row_in_archive_order":{"model":"AnyNet","paper_title":"Anytime Stereo Image Depth Estimation on Mobile Devices","paper_url":"/paper/anytime-stereo-image-depth-estimation-on","paper_date":"2018-10-26","arxiv_id":"1810.11408","code_links":[{"title":"mileyan/AnyNet","url":"https://github.com/mileyan/AnyNet"},{"title":"mamoanwar97/Anynet_modified","url":"https://github.com/mamoanwar97/Anynet_modified"},{"title":"rajeevpatwari/anynet","url":"https://github.com/rajeevpatwari/anynet"}],"syntology":{"n":26,"n_ran":3,"n_unverified":23,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/kitti","name":"KITTI","full_name":"","num_papers_in_archive":3661},{"url":"/dataset/spring","name":"Spring","full_name":"Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo","num_papers_in_archive":29},{"url":"/dataset/helvipad","name":"Helvipad","full_name":"","num_papers_in_archive":5},{"url":"/dataset/vbr","name":"VBR","full_name":"VBR: A Vision Benchmark in Rome","num_papers_in_archive":3},{"url":"/dataset/guiss-dataset","name":"GUISS dataset","full_name":"Meshes, textures, Blend files, stereo datasets, depth maps, depth estimations)","num_papers_in_archive":1},{"url":"/dataset/ms2-dataset-rgb-nir-thermal-images-lidar-gps","name":"Multi-Spectral Stereo Dataset  (RGB, NIR, thermal images, LiDAR, GPS/IMU)","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/omnnidirectional-stereo-depth-estimation","name":"Omnnidirectional Stereo Depth Estimation"}],"parent_tasks":[{"url":"/task/depth-estimation","name":"Depth Estimation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":55,"tagged_in_all":97,"items":[{"url":"/paper/factorized-attention-self-attention-with","title":"Efficient Attention: Attention with Linear Complexities","date":"2018-12-04","arxiv_id":"1812.01243","repositories_listed":14,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/hitnet-hierarchical-iterative-tile-refinement","title":"HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching","date":"2020-07-23","arxiv_id":"2007.12140","repositories_listed":9,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/pyramid-stereo-matching-network","title":"Pyramid Stereo Matching Network","date":"2018-03-23","arxiv_id":"1803.08669","repositories_listed":6,"syntology":{"n":11,"n_ran":3,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/mobilestereonet-towards-lightweight-deep","title":"MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching","date":"2021-08-22","arxiv_id":"2108.09770","repositories_listed":4,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/on-the-importance-of-stereo-for-accurate","title":"On the Importance of Stereo for Accurate Depth Estimation: An Efficient Semi-Supervised Deep Neural Network Approach","date":"2018-03-26","arxiv_id":"1803.09719","repositories_listed":4,"syntology":null},{"url":"/paper/ga-net-guided-aggregation-net-for-end-to-end","title":"GA-Net: Guided Aggregation Net for End-to-end Stereo Matching","date":"2019-04-13","arxiv_id":"1904.06587","repositories_listed":3,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/anytime-stereo-image-depth-estimation-on","title":"Anytime Stereo Image Depth Estimation on Mobile Devices","date":"2018-10-26","arxiv_id":"1810.11408","repositories_listed":3,"syntology":{"n":26,"n_ran":3,"n_unverified":23,"n_pointer_only":0}},{"url":"/paper/foundationstereo-zero-shot-stereo-matching","title":"FoundationStereo: Zero-Shot Stereo Matching","date":"2025-01-17","arxiv_id":"2501.09898","repositories_listed":2,"syntology":{"n":46,"n_ran":36,"n_unverified":10,"n_pointer_only":46}},{"url":"/paper/event-based-stereo-depth-estimation-a-survey","title":"Event-based Stereo Depth Estimation: A Survey","date":"2024-09-26","arxiv_id":"2409.17680","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/endo-4dgs-distilling-depth-ranking-for","title":"Endo-4DGS: Endoscopic Monocular Scene Reconstruction with 4D Gaussian Splatting","date":"2024-01-29","arxiv_id":"2401.16416","repositories_listed":2,"syntology":null},{"url":"/paper/spring-a-high-resolution-high-detail-dataset","title":"Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo","date":"2023-03-03","arxiv_id":"2303.01943","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/acvnet-attention-concatenation-volume-for","title":"Attention Concatenation Volume for Accurate and Efficient Stereo Matching","date":"2022-03-04","arxiv_id":"2203.02146","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/towards-continual-online-unsupervised-depth","title":"Towards Continual, Online, Self-Supervised Depth","date":"2021-02-28","arxiv_id":"2103.00369","repositories_listed":2,"syntology":null},{"url":"/paper/why-having-10000-parameters-in-your-camera","title":"Why Having 10,000 Parameters in Your Camera Model is Better Than Twelve","date":"2019-12-05","arxiv_id":"1912.02908","repositories_listed":2,"syntology":{"n":14,"n_ran":0,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/depth-estimation-in-nighttime-using-stereo","title":"Nighttime Stereo Depth Estimation using Joint Translation-Stereo Learning: Light Effects and Uninformative Regions","date":"2019-09-30","arxiv_id":"1909.13701","repositories_listed":2,"syntology":null},{"url":"/paper/stereonet-guided-hierarchical-refinement-for","title":"StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction","date":"2018-07-24","arxiv_id":"1807.08865","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":3}},{"url":"/paper/boosting-omnidirectional-stereo-matching-with","title":"Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model","date":"2025-03-30","arxiv_id":"2503.23502","repositories_listed":1,"syntology":null},{"url":"/paper/deep-depth-estimation-from-thermal-image-1","title":"Deep Depth Estimation from Thermal Image: Dataset, Benchmark, and Challenges","date":"2025-03-28","arxiv_id":"2503.22060","repositories_listed":1,"syntology":null},{"url":"/paper/helvipad-a-real-world-dataset-for","title":"Helvipad: A Real-World Dataset for Omnidirectional Stereo Depth Estimation","date":"2024-11-27","arxiv_id":"2411.18335","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-depth-estimation-for-unstable","title":"Efficient Depth Estimation for Unstable Stereo Camera Systems on AR Glasses","date":"2024-11-15","arxiv_id":"2411.10013","repositories_listed":1,"syntology":null},{"url":"/paper/dusk-till-dawn-self-supervised-nighttime","title":"Dusk Till Dawn: Self-supervised Nighttime Stereo Depth Estimation using Visual Foundation Models","date":"2024-05-18","arxiv_id":"2405.11158","repositories_listed":1,"syntology":null},{"url":"/paper/mocha-stereo-motif-channel-attention-network","title":"MoCha-Stereo: Motif Channel Attention Network for Stereo Matching","date":"2024-04-10","arxiv_id":"2404.06842","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/icy-moon-surface-simulation-and-stereo-depth","title":"Icy Moon Surface Simulation and Stereo Depth Estimation for Sampling Autonomy","date":"2024-01-23","arxiv_id":"2401.12414","repositories_listed":1,"syntology":null},{"url":"/paper/arai-mvsnet-a-multi-view-stereo-depth","title":"ARAI-MVSNet: A multi-view stereo depth estimation network with adaptive depth range and depth interval","date":"2023-08-17","arxiv_id":"2308.09022","repositories_listed":1,"syntology":null},{"url":"/paper/deep-depth-estimation-from-thermal-image","title":"Deep Depth Estimation From Thermal Image","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/energy-efficient-adaptive-3d-sensing","title":"Energy-Efficient Adaptive 3D Sensing","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-practical-stereo-depth-system-for-smart","title":"A Practical Stereo Depth System for Smart Glasses","date":"2022-11-19","arxiv_id":"2211.10551","repositories_listed":1,"syntology":null},{"url":"/paper/unifying-flow-stereo-and-depth-estimation","title":"Unifying Flow, Stereo and Depth Estimation","date":"2022-11-10","arxiv_id":"2211.05783","repositories_listed":1,"syntology":null},{"url":"/paper/context-enhanced-stereo-transformer","title":"Context-Enhanced Stereo Transformer","date":"2022-10-21","arxiv_id":"2210.11719","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/event-based-stereo-depth-estimation-from-ego","title":"Event-based Stereo Depth Estimation from Ego-motion using Ray Density Fusion","date":"2022-10-17","arxiv_id":"2210.08927","repositories_listed":1,"syntology":null}],"syntology_records":14,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}