{"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/group-wise-correlation-stereo-network","title":"Group-wise Correlation Stereo Network","arxiv_id":"1903.04025","date":"2019-03-10","proceeding":"CVPR 2019 6","authors":["Xiaoyang Guo","Kai Yang","Wukui Yang","Xiaogang Wang","Hongsheng Li"],"abstract":"Stereo matching estimates the disparity between a rectified image pair, which\nis of great importance to depth sensing, autonomous driving, and other related\ntasks. Previous works built cost volumes with cross-correlation or\nconcatenation of left and right features across all disparity levels, and then\na 2D or 3D convolutional neural network is utilized to regress the disparity\nmaps. In this paper, we propose to construct the cost volume by group-wise\ncorrelation. The left features and the right features are divided into groups\nalong the channel dimension, and correlation maps are computed among each group\nto obtain multiple matching cost proposals, which are then packed into a cost\nvolume. Group-wise correlation provides efficient representations for measuring\nfeature similarities and will not lose too much information like full\ncorrelation. It also preserves better performance when reducing parameters\ncompared with previous methods. The 3D stacked hourglass network proposed in\nprevious works is improved to boost the performance and decrease the inference\ncomputational cost. Experiment results show that our method outperforms\nprevious methods on Scene Flow, KITTI 2012, and KITTI 2015 datasets. The code\nis available at https://github.com/xy-guo/GwcNet","url_abs":"http://arxiv.org/abs/1903.04025v1","url_pdf":"http://arxiv.org/pdf/1903.04025v1.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":"group-wise-correlation-stereo-network","repo_url":"https://github.com/xy-guo/GwcNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"group-wise-correlation-stereo-network","repo_url":"https://github.com/lly00412/sednet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"stereo-matching-1","task_name":"Stereo Matching"},{"task_slug":"stereo-matching","task_name":"Stereo Matching Hand"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"hourglass-module","method_name":"Hourglass Module"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"stacked-hourglass-network","method_name":"Stacked Hourglass Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.04025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.04025"}},"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/lly00412/sednet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xy-guo/GwcNet","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1}},"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":"53fc891ba9c195d6","entry":"GwcNet_G","repo":"xy-guo/GwcNet","repo_kind":"official","path":"models/gwcnet.py","file_url":"https://github.com/xy-guo/GwcNet/blob/HEAD/models/gwcnet.py","link_basis":"first_harvest_node","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":"53fc891ba9c195d6"}},{"code_sha256_prefix":"9a27f8c009f91213","entry":"GwcNet_GC","repo":"xy-guo/GwcNet","repo_kind":"official","path":"models/gwcnet.py","file_url":"https://github.com/xy-guo/GwcNet/blob/HEAD/models/gwcnet.py","link_basis":"first_harvest_node","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":"9a27f8c009f91213"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}