{"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/aanet-adaptive-aggregation-network-for","title":"AANet: Adaptive Aggregation Network for Efficient Stereo Matching","arxiv_id":"2004.09548","date":"2020-04-20","proceeding":"CVPR 2020 6","authors":["Haofei Xu","Juyong Zhang"],"abstract":"Despite the remarkable progress made by learning based stereo matching algorithms, one key challenge remains unsolved. Current state-of-the-art stereo models are mostly based on costly 3D convolutions, the cubic computational complexity and high memory consumption make it quite expensive to deploy in real-world applications. In this paper, we aim at completely replacing the commonly used 3D convolutions to achieve fast inference speed while maintaining comparable accuracy. To this end, we first propose a sparse points based intra-scale cost aggregation method to alleviate the well-known edge-fattening issue at disparity discontinuities. Further, we approximate traditional cross-scale cost aggregation algorithm with neural network layers to handle large textureless regions. Both modules are simple, lightweight, and complementary, leading to an effective and efficient architecture for cost aggregation. With these two modules, we can not only significantly speed up existing top-performing models (e.g., $41\\times$ than GC-Net, $4\\times$ than PSMNet and $38\\times$ than GA-Net), but also improve the performance of fast stereo models (e.g., StereoNet). We also achieve competitive results on Scene Flow and KITTI datasets while running at 62ms, demonstrating the versatility and high efficiency of the proposed method. Our full framework is available at https://github.com/haofeixu/aanet .","url_abs":"https://arxiv.org/abs/2004.09548v1","url_pdf":"https://arxiv.org/pdf/2004.09548v1.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":"aanet-adaptive-aggregation-network-for","repo_url":"https://github.com/haofeixu/aanet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"scene-flow-estimation","task_name":"Scene Flow Estimation"},{"task_slug":"stereo-disparity-estimation","task_name":"Stereo Disparity Estimation"},{"task_slug":"stereo-matching-1","task_name":"Stereo Matching"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-flow-estimation-on-scene-flow","task":"Scene Flow Estimation","dataset":"Scene Flow","model":"AANet","rank_in_archive_order":1,"of":1,"metrics":{"EPE":"0.068"},"uses_additional_data":false},{"leaderboard":"/sota/stereo-disparity-estimation-on-scene-flow","task":"Stereo Disparity Estimation","dataset":"Scene Flow","model":"AANet","rank_in_archive_order":1,"of":7,"metrics":{"EPE":"0.87","one pixel error":"9.3"},"uses_additional_data":false},{"leaderboard":"/sota/stereo-disparity-estimation-on-scene-flow","task":"Stereo Disparity Estimation","dataset":"Scene Flow","model":"AANet+","rank_in_archive_order":3,"of":7,"metrics":{"EPE":"0.72","one pixel error":"7.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.09548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.09548"}},"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/haofeixu/aanet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran":7,"unverified":5},"by_repo_kind":{"official":{"samples":14,"ran":9,"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":"d9def42110729a85","entry":"conv1x1","repo":"haofeixu/aanet","repo_kind":"official","path":"nets/deform.py","file_url":"https://github.com/haofeixu/aanet/blob/HEAD/nets/deform.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"8182b8e2a441abbd","entry":"conv1x1","repo":"haofeixu/aanet","repo_kind":"official","path":"nets/feature.py","file_url":"https://github.com/haofeixu/aanet/blob/HEAD/nets/feature.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8182b8e2a441abbd"}},{"code_sha256_prefix":"2c4f90d71c073dfe","entry":"conv2d","repo":"haofeixu/aanet","repo_kind":"official","path":"nets/aggregation.py","file_url":"https://github.com/haofeixu/aanet/blob/HEAD/nets/aggregation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2c4f90d71c073dfe"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"haofeixu/aanet","repo_kind":"official","path":"nets/deform.py","file_url":"https://github.com/haofeixu/aanet/blob/HEAD/nets/deform.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"160bb14bd76201b4"}},{"code_sha256_prefix":"9fba66e062846970","entry":"conv3x3","repo":"haofeixu/aanet","repo_kind":"official","path":"nets/feature.py","file_url":"https://github.com/haofeixu/aanet/blob/HEAD/nets/feature.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9fba66e062846970"}},{"code_sha256_prefix":"af5d1e93b7cc0884","entry":"conv5x5","repo":"haofeixu/aanet","repo_kind":"official","path":"nets/feature.py","file_url":"https://github.com/haofeixu/aanet/blob/HEAD/nets/feature.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"af5d1e93b7cc0884"}},{"code_sha256_prefix":"46674adf87c5459d","entry":"convbn_3d","repo":"haofeixu/aanet","repo_kind":"official","path":"nets/aggregation.py","file_url":"https://github.com/haofeixu/aanet/blob/HEAD/nets/aggregation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"46674adf87c5459d"}},{"code_sha256_prefix":"d264efc1788f1659","entry":"meshgrid","repo":"haofeixu/aanet","repo_kind":"official","path":"nets/warp.py","file_url":"https://github.com/haofeixu/aanet/blob/HEAD/nets/warp.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d264efc1788f1659"}},{"code_sha256_prefix":"62da485d08a1a205","entry":"normalize_coords","repo":"haofeixu/aanet","repo_kind":"official","path":"nets/warp.py","file_url":"https://github.com/haofeixu/aanet/blob/HEAD/nets/warp.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"62da485d08a1a205"}},{"code_sha256_prefix":"81a0c67776f66692","entry":"conv3d","repo":"haofeixu/aanet","repo_kind":"official","path":"nets/aggregation.py","file_url":"https://github.com/haofeixu/aanet/blob/HEAD/nets/aggregation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81a0c67776f66692"}},{"code_sha256_prefix":"3472053ffc0cd145","entry":"d1_metric","repo":"haofeixu/aanet","repo_kind":"official","path":"metric.py","file_url":"https://github.com/haofeixu/aanet/blob/HEAD/metric.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3472053ffc0cd145"}},{"code_sha256_prefix":"bdb566fe49732f09","entry":"disp_warp","repo":"haofeixu/aanet","repo_kind":"official","path":"nets/warp.py","file_url":"https://github.com/haofeixu/aanet/blob/HEAD/nets/warp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bdb566fe49732f09"}},{"code_sha256_prefix":"de7db437cc7b6ca0","entry":"epe_metric","repo":"haofeixu/aanet","repo_kind":"official","path":"metric.py","file_url":"https://github.com/haofeixu/aanet/blob/HEAD/metric.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"de7db437cc7b6ca0"}},{"code_sha256_prefix":"a2ed1ebdb4d69030","entry":"thres_metric","repo":"haofeixu/aanet","repo_kind":"official","path":"metric.py","file_url":"https://github.com/haofeixu/aanet/blob/HEAD/metric.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a2ed1ebdb4d69030"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}