{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/hitnet-hierarchical-iterative-tile-refinement","title":"HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching","arxiv_id":"2007.12140","date":"2020-07-23","proceeding":"CVPR 2021 1","authors":["Vladimir Tankovich","Christian Häne","yinda zhang","Adarsh Kowdle","Sean Fanello","Sofien Bouaziz"],"abstract":"This paper presents HITNet, a novel neural network architecture for real-time stereo matching. Contrary to many recent neural network approaches that operate on a full cost volume and rely on 3D convolutions, our approach does not explicitly build a volume and instead relies on a fast multi-resolution initialization step, differentiable 2D geometric propagation and warping mechanisms to infer disparity hypotheses. To achieve a high level of accuracy, our network not only geometrically reasons about disparities but also infers slanted plane hypotheses allowing to more accurately perform geometric warping and upsampling operations. Our architecture is inherently multi-resolution allowing the propagation of information across different levels. Multiple experiments prove the effectiveness of the proposed approach at a fraction of the computation required by state-of-the-art methods. At the time of writing, HITNet ranks 1st-3rd on all the metrics published on the ETH3D website for two view stereo, ranks 1st on most of the metrics among all the end-to-end learning approaches on Middlebury-v3, ranks 1st on the popular KITTI 2012 and 2015 benchmarks among the published methods faster than 100ms.","url_abs":"https://arxiv.org/abs/2007.12140v5","url_pdf":"https://arxiv.org/pdf/2007.12140v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"hitnet-hierarchical-iterative-tile-refinement","repo_url":"https://github.com/google-research/google-research","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"hitnet-hierarchical-iterative-tile-refinement","repo_url":"https://github.com/google-research/google-research/tree/master/hitnet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"hitnet-hierarchical-iterative-tile-refinement","repo_url":"https://github.com/ibaiGorordo/HITNET-Stereo-Depth-estimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hitnet-hierarchical-iterative-tile-refinement","repo_url":"https://github.com/ibaiGorordo/ONNX-HITNET-Stereo-Depth-estimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hitnet-hierarchical-iterative-tile-refinement","repo_url":"https://github.com/ibaiGorordo/TFLite-HITNET-Stereo-depth-estimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hitnet-hierarchical-iterative-tile-refinement","repo_url":"https://github.com/jiaxiZeng/Temporally-Consistent-Stereo-Matching","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hitnet-hierarchical-iterative-tile-refinement","repo_url":"https://github.com/ibaiGorordo/TfLite-Ultra-Fast-Lane-Detection-Inference","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hitnet-hierarchical-iterative-tile-refinement","repo_url":"https://github.com/meteorshowers/X-StereoLab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"hitnet-hierarchical-iterative-tile-refinement","repo_url":"https://github.com/zjjMaiMai/TinyHITNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"stereo-depth-estimation","task_name":"Stereo Depth Estimation"},{"task_slug":"stereo-disparity-estimation","task_name":"Stereo Disparity Estimation"},{"task_slug":"stereo-matching-1","task_name":"Stereo Matching"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"hitnet","method_name":"HITNet"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[{"slug":"hitnet","name":"HITNet","full_name":"HITNet"}],"results":[{"leaderboard":"/sota/stereo-depth-estimation-on-kitti2015","task":"Stereo Depth Estimation","dataset":"KITTI2015","model":"HITNET","rank_in_archive_order":4,"of":7,"metrics":{"three pixel error":"2.43"},"uses_additional_data":false},{"leaderboard":"/sota/stereo-disparity-estimation-on-scene-flow","task":"Stereo Disparity Estimation","dataset":"Scene Flow","model":"HITNet","rank_in_archive_order":5,"of":7,"metrics":{"EPE":"0.529","one pixel error":"5.52","three pixel error":"3.00"},"uses_additional_data":false},{"leaderboard":"/sota/stereo-disparity-estimation-on-scene-flow","task":"Stereo Disparity Estimation","dataset":"Scene Flow","model":"HITNet L","rank_in_archive_order":6,"of":7,"metrics":{"EPE":"0.43","one pixel error":"4.70","three pixel error":"2.57"},"uses_additional_data":false},{"leaderboard":"/sota/stereo-disparity-estimation-on-scene-flow","task":"Stereo Disparity Estimation","dataset":"Scene Flow","model":"HITNet XL","rank_in_archive_order":7,"of":7,"metrics":{"EPE":"0.36","one pixel error":"4.09","three pixel error":"2.21"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.12140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.12140"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/google-research","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zjjMaiMai/TinyHITNet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ibaiGorordo/TfLite-Ultra-Fast-Lane-Detection-Inference","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/meteorshowers/X-StereoLab","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ibaiGorordo/HITNET-Stereo-Depth-estimation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiaxiZeng/Temporally-Consistent-Stereo-Matching","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ibaiGorordo/TFLite-HITNET-Stereo-depth-estimation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/google-research/tree/master/hitnet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ibaiGorordo/ONNX-HITNET-Stereo-Depth-estimation","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"unverified":4},"by_repo_kind":{"listed":{"samples":5,"ran":1,"repositories":3}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"06fca4c705811abe","entry":"main_process","repo":"meteorshowers/X-StereoLab","repo_kind":"listed","path":"tools/train_net_disp.py","file_url":"https://github.com/meteorshowers/X-StereoLab/blob/HEAD/tools/train_net_disp.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"06fca4c705811abe"}},{"code_sha256_prefix":"8bb7fe039a0dd8bf","entry":"draw_depth","repo":"ibaiGorordo/HITNET-Stereo-Depth-estimation","repo_kind":"listed","path":"hitnet/utils_hitnet.py","file_url":"https://github.com/ibaiGorordo/HITNET-Stereo-Depth-estimation/blob/HEAD/hitnet/utils_hitnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8bb7fe039a0dd8bf"}},{"code_sha256_prefix":"c95dbd0cf81d5fa9","entry":"draw_disparity","repo":"ibaiGorordo/HITNET-Stereo-Depth-estimation","repo_kind":"listed","path":"hitnet/utils_hitnet.py","file_url":"https://github.com/ibaiGorordo/HITNET-Stereo-Depth-estimation/blob/HEAD/hitnet/utils_hitnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c95dbd0cf81d5fa9"}},{"code_sha256_prefix":"21ab4fa6af33f75f","entry":"load_img","repo":"ibaiGorordo/TFLite-HITNET-Stereo-depth-estimation","repo_kind":"listed","path":"hitnet/utils_hitnet.py","file_url":"https://github.com/ibaiGorordo/TFLite-HITNET-Stereo-depth-estimation/blob/HEAD/hitnet/utils_hitnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"21ab4fa6af33f75f"}},{"code_sha256_prefix":"713d88a6d30f8420","entry":"wrap_frozen_graph","repo":"ibaiGorordo/HITNET-Stereo-Depth-estimation","repo_kind":"listed","path":"hitnet/utils_hitnet.py","file_url":"https://github.com/ibaiGorordo/HITNET-Stereo-Depth-estimation/blob/HEAD/hitnet/utils_hitnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"713d88a6d30f8420"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}