{"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/ga-net-guided-aggregation-net-for-end-to-end","title":"GA-Net: Guided Aggregation Net for End-to-end Stereo Matching","arxiv_id":"1904.06587","date":"2019-04-13","proceeding":"CVPR 2019 6","authors":["Feihu Zhang","Victor Prisacariu","Ruigang Yang","Philip H. S. Torr"],"abstract":"In the stereo matching task, matching cost aggregation is crucial in both\ntraditional methods and deep neural network models in order to accurately\nestimate disparities. We propose two novel neural net layers, aimed at\ncapturing local and the whole-image cost dependencies respectively. The first\nis a semi-global aggregation layer which is a differentiable approximation of\nthe semi-global matching, the second is the local guided aggregation layer\nwhich follows a traditional cost filtering strategy to refine thin structures.\nThese two layers can be used to replace the widely used 3D convolutional layer\nwhich is computationally costly and memory-consuming as it has cubic\ncomputational/memory complexity. In the experiments, we show that nets with a\ntwo-layer guided aggregation block easily outperform the state-of-the-art\nGC-Net which has nineteen 3D convolutional layers. We also train a deep guided\naggregation network (GA-Net) which gets better accuracies than state-of-the-art\nmethods on both Scene Flow dataset and KITTI benchmarks.","url_abs":"http://arxiv.org/abs/1904.06587v1","url_pdf":"http://arxiv.org/pdf/1904.06587v1.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":"ga-net-guided-aggregation-net-for-end-to-end","repo_url":"https://github.com/feihuzhang/GANet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"ga-net-guided-aggregation-net-for-end-to-end","repo_url":"https://github.com/HKBU-HPML/FADNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"ga-net-guided-aggregation-net-for-end-to-end","repo_url":"https://github.com/skumailraza/FRSNet-GA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"stereo-depth-estimation","task_name":"Stereo Depth Estimation"},{"task_slug":"stereo-matching-1","task_name":"Stereo Matching"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/stereo-depth-estimation-on-spring","task":"Stereo Depth Estimation","dataset":"Spring","model":"GA-Net","rank_in_archive_order":4,"of":4,"metrics":{"1px total":"23.225"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1904.06587","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.06587"}},"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/skumailraza/FRSNet-GA","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/feihuzhang/GANet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HKBU-HPML/FADNet","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3,"ran_honours":1,"ran_fixture":2,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":5,"ran":4,"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":"f5033afda061ae4f","entry":"load_data","repo":"skumailraza/FRSNet-GA","repo_kind":"listed","path":"predict.py","file_url":"https://github.com/skumailraza/FRSNet-GA/blob/HEAD/predict.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f5033afda061ae4f"}},{"code_sha256_prefix":"49a628e53f46ed75","entry":"load_data","repo":"feihuzhang/GANet","repo_kind":"official","path":"predict.py","file_url":"https://github.com/feihuzhang/GANet/blob/HEAD/predict.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"49a628e53f46ed75"}},{"code_sha256_prefix":"259c1efb59c8cc6f","entry":"readPFM","repo":"feihuzhang/GANet","repo_kind":"official","path":"evaluation.py","file_url":"https://github.com/feihuzhang/GANet/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"259c1efb59c8cc6f"}},{"code_sha256_prefix":"8bba59acb98c1899","entry":"readPNG","repo":"skumailraza/FRSNet-GA","repo_kind":"listed","path":"evaluation.py","file_url":"https://github.com/skumailraza/FRSNet-GA/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8bba59acb98c1899"}},{"code_sha256_prefix":"a20b38ce75ecff0e","entry":"test_transform","repo":"skumailraza/FRSNet-GA","repo_kind":"listed","path":"predict.py","file_url":"https://github.com/skumailraza/FRSNet-GA/blob/HEAD/predict.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a20b38ce75ecff0e"}},{"code_sha256_prefix":"674d035839049ef2","entry":"test_transform","repo":"skumailraza/FRSNet-GA","repo_kind":"listed","path":"evaluation.py","file_url":"https://github.com/skumailraza/FRSNet-GA/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"674d035839049ef2"}},{"code_sha256_prefix":"e614bb1349b10c4f","entry":"readPFM","repo":"skumailraza/FRSNet-GA","repo_kind":"listed","path":"evaluation.py","file_url":"https://github.com/skumailraza/FRSNet-GA/blob/HEAD/evaluation.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":"e614bb1349b10c4f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}