{"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/aa-rmvsnet-adaptive-aggregation-recurrent","title":"AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network","arxiv_id":"2108.03824","date":"2021-08-09","proceeding":"ICCV 2021 10","authors":["Zizhuang Wei","Qingtian Zhu","Chen Min","Yisong Chen","Guoping Wang"],"abstract":"In this paper, we present a novel recurrent multi-view stereo network based on long short-term memory (LSTM) with adaptive aggregation, namely AA-RMVSNet. We firstly introduce an intra-view aggregation module to adaptively extract image features by using context-aware convolution and multi-scale aggregation, which efficiently improves the performance on challenging regions, such as thin objects and large low-textured surfaces. To overcome the difficulty of varying occlusion in complex scenes, we propose an inter-view cost volume aggregation module for adaptive pixel-wise view aggregation, which is able to preserve better-matched pairs among all views. The two proposed adaptive aggregation modules are lightweight, effective and complementary regarding improving the accuracy and completeness of 3D reconstruction. Instead of conventional 3D CNNs, we utilize a hybrid network with recurrent structure for cost volume regularization, which allows high-resolution reconstruction and finer hypothetical plane sweep. The proposed network is trained end-to-end and achieves excellent performance on various datasets. It ranks $1^{st}$ among all submissions on Tanks and Temples benchmark and achieves competitive results on DTU dataset, which exhibits strong generalizability and robustness. Implementation of our method is available at https://github.com/QT-Zhu/AA-RMVSNet.","url_abs":"https://arxiv.org/abs/2108.03824v1","url_pdf":"https://arxiv.org/pdf/2108.03824v1.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":"aa-rmvsnet-adaptive-aggregation-recurrent","repo_url":"https://github.com/qt-zhu/aa-rmvsnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"point-clouds","task_name":"Point Clouds"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-reconstruction-on-dtu","task":"3D Reconstruction","dataset":"DTU","model":"AA-RMVSNet","rank_in_archive_order":19,"of":24,"metrics":{"Acc":"0.376","Comp":"0.339","Overall":"0.357"},"uses_additional_data":false},{"leaderboard":"/sota/point-clouds-on-tanks-and-temples","task":"Point Clouds","dataset":"Tanks and Temples","model":"AA-RMVSNet","rank_in_archive_order":16,"of":21,"metrics":{"Mean F1 (Intermediate)":"61.51"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.03824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.03824"}},"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/qt-zhu/aa-rmvsnet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/QT-Zhu/AA-RMVSNet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_fixture":1,"unverified":16},"by_repo_kind":{"official":{"samples":20,"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":"e23d1383c35bf5b7","entry":"convgnrelu","repo":"qt-zhu/aa-rmvsnet","repo_kind":"official","path":"models/module.py","file_url":"https://github.com/qt-zhu/aa-rmvsnet/blob/HEAD/models/module.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e23d1383c35bf5b7"}},{"code_sha256_prefix":"b62bec09ceeaca79","entry":"make_recursive_func","repo":"qt-zhu/aa-rmvsnet","repo_kind":"official","path":"utils.py","file_url":"https://github.com/qt-zhu/aa-rmvsnet/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b62bec09ceeaca79"}},{"code_sha256_prefix":"a1db096963f65ed2","entry":"read_img","repo":"qt-zhu/aa-rmvsnet","repo_kind":"official","path":"fusion.py","file_url":"https://github.com/qt-zhu/aa-rmvsnet/blob/HEAD/fusion.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a1db096963f65ed2"}},{"code_sha256_prefix":"30bd7e828f7917d6","entry":"scale_camera","repo":"qt-zhu/aa-rmvsnet","repo_kind":"official","path":"datasets/preprocess.py","file_url":"https://github.com/qt-zhu/aa-rmvsnet/blob/HEAD/datasets/preprocess.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"30bd7e828f7917d6"}},{"code_sha256_prefix":"11b79c8329f07c31","entry":"AARMVSNet","repo":"QT-Zhu/AA-RMVSNet","repo_kind":"official","path":"models/drmvsnet.py","file_url":"https://github.com/QT-Zhu/AA-RMVSNet/blob/HEAD/models/drmvsnet.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":"11b79c8329f07c31"}},{"code_sha256_prefix":"90c1b6385c83bf65","entry":"FeatNet","repo":"QT-Zhu/AA-RMVSNet","repo_kind":"official","path":"models/drmvsnet.py","file_url":"https://github.com/QT-Zhu/AA-RMVSNet/blob/HEAD/models/drmvsnet.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":"90c1b6385c83bf65"}},{"code_sha256_prefix":"48519afbe609107e","entry":"InterViewAAModule","repo":"QT-Zhu/AA-RMVSNet","repo_kind":"official","path":"models/drmvsnet.py","file_url":"https://github.com/QT-Zhu/AA-RMVSNet/blob/HEAD/models/drmvsnet.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":"48519afbe609107e"}},{"code_sha256_prefix":"df42d9acf0c97aae","entry":"IntraViewAAModule","repo":"QT-Zhu/AA-RMVSNet","repo_kind":"official","path":"models/drmvsnet.py","file_url":"https://github.com/QT-Zhu/AA-RMVSNet/blob/HEAD/models/drmvsnet.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":"df42d9acf0c97aae"}},{"code_sha256_prefix":"acd3e51d785ce7a3","entry":"UNetConvLSTM","repo":"QT-Zhu/AA-RMVSNet","repo_kind":"official","path":"models/drmvsnet.py","file_url":"https://github.com/QT-Zhu/AA-RMVSNet/blob/HEAD/models/drmvsnet.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":"acd3e51d785ce7a3"}},{"code_sha256_prefix":"98db92623ad957c3","entry":"deformconvgnrelu","repo":"qt-zhu/aa-rmvsnet","repo_kind":"official","path":"models/module.py","file_url":"https://github.com/qt-zhu/aa-rmvsnet/blob/HEAD/models/module.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":"98db92623ad957c3"}},{"code_sha256_prefix":"b44954d20d02d2e4","entry":"homo_warping_depthwise","repo":"qt-zhu/aa-rmvsnet","repo_kind":"official","path":"models/module.py","file_url":"https://github.com/qt-zhu/aa-rmvsnet/blob/HEAD/models/module.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":"b44954d20d02d2e4"}},{"code_sha256_prefix":"74cc00801184ef89","entry":"make_nograd_func","repo":"qt-zhu/aa-rmvsnet","repo_kind":"official","path":"utils.py","file_url":"https://github.com/qt-zhu/aa-rmvsnet/blob/HEAD/utils.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":"74cc00801184ef89"}},{"code_sha256_prefix":"c299517da2bbf7f0","entry":"mvsnet_cls_loss","repo":"qt-zhu/aa-rmvsnet","repo_kind":"official","path":"models/drmvsnet.py","file_url":"https://github.com/qt-zhu/aa-rmvsnet/blob/HEAD/models/drmvsnet.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":"c299517da2bbf7f0"}},{"code_sha256_prefix":"681f7cd39c206d61","entry":"read_camera_parameters","repo":"qt-zhu/aa-rmvsnet","repo_kind":"official","path":"fusion.py","file_url":"https://github.com/qt-zhu/aa-rmvsnet/blob/HEAD/fusion.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":"681f7cd39c206d61"}},{"code_sha256_prefix":"d061d58c522d1c06","entry":"read_camera_parameters","repo":"qt-zhu/aa-rmvsnet","repo_kind":"official","path":"fusion_padding.py","file_url":"https://github.com/qt-zhu/aa-rmvsnet/blob/HEAD/fusion_padding.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":"d061d58c522d1c06"}},{"code_sha256_prefix":"0f854820f8ad0c45","entry":"read_pair_file","repo":"qt-zhu/aa-rmvsnet","repo_kind":"official","path":"fusion.py","file_url":"https://github.com/qt-zhu/aa-rmvsnet/blob/HEAD/fusion.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":"0f854820f8ad0c45"}},{"code_sha256_prefix":"6b687b02c05fe850","entry":"read_pfm","repo":"qt-zhu/aa-rmvsnet","repo_kind":"official","path":"datasets/data_io.py","file_url":"https://github.com/qt-zhu/aa-rmvsnet/blob/HEAD/datasets/data_io.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":"6b687b02c05fe850"}},{"code_sha256_prefix":"ae0bb51b7bd4b936","entry":"scale_image","repo":"qt-zhu/aa-rmvsnet","repo_kind":"official","path":"datasets/preprocess.py","file_url":"https://github.com/qt-zhu/aa-rmvsnet/blob/HEAD/datasets/preprocess.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":"ae0bb51b7bd4b936"}},{"code_sha256_prefix":"9e5eb5186f8cd22c","entry":"scale_mvs_input","repo":"qt-zhu/aa-rmvsnet","repo_kind":"official","path":"datasets/preprocess.py","file_url":"https://github.com/qt-zhu/aa-rmvsnet/blob/HEAD/datasets/preprocess.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":"9e5eb5186f8cd22c"}},{"code_sha256_prefix":"3f2fbbdcfe31adc4","entry":"tensor2float","repo":"qt-zhu/aa-rmvsnet","repo_kind":"official","path":"utils.py","file_url":"https://github.com/qt-zhu/aa-rmvsnet/blob/HEAD/utils.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":"3f2fbbdcfe31adc4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}