{"url":"/task/stereo-matching-1","name":"Stereo Matching","slug":"stereo-matching-1","description_markdown":"**Stereo Matching** is one of the core technologies in computer vision, which recovers 3D structures of real world from 2D images. It has been widely used in areas such as autonomous driving, augmented reality and robotics navigation. Given a pair of rectified stereo images, the goal of Stereo Matching is to compute the disparity for each pixel in the reference image, where disparity is defined as the horizontal displacement between a pair of corresponding pixels in the left and right images.\r\n\r\n\r\n<span class=\"description-source\">Source: [Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching ](https://arxiv.org/abs/1909.03751)</span>","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":517,"papers_with_code":192,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":20,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/virtual-kitti","name":"Virtual KITTI","full_name":"","num_papers_in_archive":133},{"url":"/dataset/eth3d","name":"ETH3D","full_name":"","num_papers_in_archive":121},{"url":"/dataset/middlebury-2014","name":"Middlebury 2014","full_name":"Middlebury 2014","num_papers_in_archive":59},{"url":"/dataset/virtual-kitti-2","name":"Virtual KITTI 2","full_name":"","num_papers_in_archive":53},{"url":"/dataset/drivingstereo","name":"DrivingStereo","full_name":"","num_papers_in_archive":50},{"url":"/dataset/pst900","name":"PST900","full_name":null,"num_papers_in_archive":35},{"url":"/dataset/imc-phototourism","name":"IMC PhotoTourism","full_name":"Image Matching Challenge Phototourism","num_papers_in_archive":14},{"url":"/dataset/3d-ken-burns","name":"3D Ken Burns","full_name":"","num_papers_in_archive":13},{"url":"/dataset/irs","name":"IRS","full_name":"Indoor Robotics Stereo","num_papers_in_archive":12},{"url":"/dataset/cats","name":"CATS","full_name":"Color and Thermal Stereo Benchmark","num_papers_in_archive":11},{"url":"/dataset/middlebury-2005","name":"Middlebury 2005","full_name":"Middlebury 2005","num_papers_in_archive":9},{"url":"/dataset/helvipad","name":"Helvipad","full_name":"","num_papers_in_archive":5},{"url":"/dataset/middlebury-2006","name":"Middlebury 2006","full_name":"Middlebury 2006","num_papers_in_archive":5},{"url":"/dataset/middlebury-2001","name":"Middlebury 2001","full_name":"Middlebury 2001","num_papers_in_archive":4},{"url":"/dataset/uasol","name":"UASOL","full_name":"A large-scale high-resolution outdoor stereo dataset","num_papers_in_archive":3},{"url":"/dataset/vbr","name":"VBR","full_name":"VBR: A Vision Benchmark in Rome","num_papers_in_archive":3},{"url":"/dataset/plittersdorf","name":"Plittersdorf","full_name":"","num_papers_in_archive":2},{"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/imcpt-sparsegm-100","name":"IMCPT-SparseGM-100","full_name":"","num_papers_in_archive":1},{"url":"/dataset/imcpt-sparsegm","name":"IMCPT-SparseGM-50","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/stereo-disparity-estimation","name":"Stereo Disparity 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":192,"tagged_in_all":517,"items":[{"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/cascade-cost-volume-for-high-resolution-multi","title":"Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching","date":"2019-12-13","arxiv_id":"1912.06378","repositories_listed":4,"syntology":{"n":14,"n_ran":6,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/efficient-deep-learning-for-stereo-matching","title":"Efficient Deep Learning for Stereo Matching","date":"2016-06-01","arxiv_id":null,"repositories_listed":4,"syntology":null},{"url":"/paper/accurate-and-efficient-stereo-matching-via","title":"Accurate and Efficient Stereo Matching via Attention Concatenation Volume","date":"2022-09-23","arxiv_id":"2209.12699","repositories_listed":3,"syntology":{"n":11,"n_ran":4,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/practical-stereo-matching-via-cascaded","title":"Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation","date":"2022-03-22","arxiv_id":"2203.11483","repositories_listed":3,"syntology":{"n":12,"n_ran":8,"n_unverified":4,"n_pointer_only":11}},{"url":"/paper/cfnet-cascade-and-fused-cost-volume-for","title":"CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching","date":"2021-04-09","arxiv_id":"2104.04314","repositories_listed":3,"syntology":{"n":21,"n_ran":4,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/displacement-invariant-matching-cost-learning","title":"Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation","date":"2020-10-28","arxiv_id":"2010.14851","repositories_listed":3,"syntology":{"n":12,"n_ran":4,"n_unverified":8,"n_pointer_only":0}},{"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/noise-aware-unsupervised-deep-lidar-stereo","title":"Noise-Aware Unsupervised Deep Lidar-Stereo Fusion","date":"2019-04-08","arxiv_id":"1904.03868","repositories_listed":3,"syntology":null},{"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/igev-iterative-multi-range-geometry-encoding","title":"IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching","date":"2024-09-01","arxiv_id":"2409.00638","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/bdis-bayesian-dense-inverse-searching-method","title":"BDIS: Bayesian Dense Inverse Searching Method for Real-Time Stereo Surgical Image Matching","date":"2022-05-06","arxiv_id":"2205.03133","repositories_listed":2,"syntology":null},{"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/smd-nets-stereo-mixture-density-networks","title":"SMD-Nets: Stereo Mixture Density Networks","date":"2021-04-08","arxiv_id":"2104.03866","repositories_listed":2,"syntology":{"n":28,"n_ran":15,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/yolostereo3d-a-step-back-to-2d-for-efficient","title":"YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection","date":"2021-03-17","arxiv_id":"2103.09422","repositories_listed":2,"syntology":null},{"url":"/paper/parallax-attention-for-unsupervised-stereo","title":"Parallax Attention for Unsupervised Stereo Correspondence Learning","date":"2020-09-16","arxiv_id":"2009.08250","repositories_listed":2,"syntology":null},{"url":"/paper/learning-stereo-from-single-images","title":"Learning Stereo from Single Images","date":"2020-08-04","arxiv_id":"2008.01484","repositories_listed":2,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/msmd-net-deep-stereo-matching-with-multi","title":"PCW-Net: Pyramid Combination and Warping Cost Volume for Stereo Matching","date":"2020-06-23","arxiv_id":"2006.12797","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/fadnet-a-fast-and-accurate-network-for","title":"FADNet: A Fast and Accurate Network for Disparity Estimation","date":"2020-03-24","arxiv_id":"2003.10758","repositories_listed":2,"syntology":null},{"url":"/paper/learning-inverse-depth-regression-for-multi","title":"Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume","date":"2019-12-26","arxiv_id":"1912.11746","repositories_listed":2,"syntology":null},{"url":"/paper/hierarchical-deep-stereo-matching-on-high-1","title":"Hierarchical Deep Stereo Matching on High-resolution Images","date":"2019-12-13","arxiv_id":"1912.06704","repositories_listed":2,"syntology":{"n":10,"n_ran":2,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/asv-accelerated-stereo-vision-system","title":"ASV: Accelerated Stereo Vision System","date":"2019-11-15","arxiv_id":"1911.07919","repositories_listed":2,"syntology":null},{"url":"/paper/adaptive-unimodal-cost-volume-filtering-for","title":"Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching","date":"2019-09-09","arxiv_id":"1909.03751","repositories_listed":2,"syntology":null},{"url":"/paper/omnimvs-end-to-end-learning-for","title":"OmniMVS: End-to-End Learning for Omnidirectional Stereo Matching","date":"2019-08-17","arxiv_id":"1908.06257","repositories_listed":2,"syntology":null},{"url":"/paper/group-wise-correlation-stereo-network","title":"Group-wise Correlation Stereo Network","date":"2019-03-10","arxiv_id":"1903.04025","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/hierarchical-discrete-distribution","title":"Hierarchical Discrete Distribution Decomposition for Match Density Estimation","date":"2018-12-15","arxiv_id":"1812.06264","repositories_listed":2,"syntology":{"n":14,"n_ran":2,"n_unverified":12,"n_pointer_only":0}},{"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}}],"syntology_records":20,"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"}}