{"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/mgdepth-motion-guided-cost-volume-for-self","title":"Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic Scenes","arxiv_id":"2312.15268","date":"2023-12-23","proceeding":null,"authors":["Kaichen Zhou","Jia-Wang Bian","Jian-Qing Zheng","JiaXing Zhong","Qian Xie","Niki Trigoni","Andrew Markham"],"abstract":"Despite advancements in self-supervised monocular depth estimation, challenges persist in dynamic scenarios due to the dependence on assumptions about a static world. In this paper, we present Manydepth2, to achieve precise depth estimation for both dynamic objects and static backgrounds, all while maintaining computational efficiency. To tackle the challenges posed by dynamic content, we incorporate optical flow and coarse monocular depth to create a pseudo-static reference frame. This frame is then utilized to build a motion-aware cost volume in collaboration with the vanilla target frame. Furthermore, to improve the accuracy and robustness of the network architecture, we propose an attention-based depth network that effectively integrates information from feature maps at different resolutions by incorporating both channel and non-local attention mechanisms. Compared to methods with similar computational costs, Manydepth2 achieves a significant reduction of approximately five percent in root-mean-square error for self-supervised monocular depth estimation on the KITTI-2015 dataset. The code could be found at https://github.com/kaichen-z/Manydepth2.","url_abs":"https://arxiv.org/abs/2312.15268v8","url_pdf":"https://arxiv.org/pdf/2312.15268v8.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":"mgdepth-motion-guided-cost-volume-for-self","repo_url":"https://github.com/kaichen-z/rad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"camera-pose-estimation","task_name":"Camera Pose Estimation"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/camera-pose-estimation-on-kitti-odometry","task":"Camera Pose Estimation","dataset":"KITTI Odometry Benchmark","model":"Manydepth2","rank_in_archive_order":1,"of":7,"metrics":{"Average Rotational Error er[%]":"2.205","Average Translational Error et[%]":"7.15"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-cityscapes","task":"Monocular Depth Estimation","dataset":"Cityscapes","model":"Manydepth2","rank_in_archive_order":2,"of":3,"metrics":{"Absolute relative error (AbsRel)":"0.097","RMSE":"5.827 ","RMSE log":"0.154","Square relative error (SqRel)":"0.792"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split","model":"Manydepth2","rank_in_archive_order":49,"of":79,"metrics":{"Delta < 1.25":"0.909","Delta < 1.25^2":"0.968","Delta < 1.25^3":"0.984","RMSE":"4.232","RMSE log":"0.649","Sq Rel":"0.170","absolute relative error":"0.091"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen-1","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split unsupervised","model":"Manydepth2(M+640x192)","rank_in_archive_order":8,"of":55,"metrics":{"Delta < 1.25":"0.909","Delta < 1.25^2":"0.968","Delta < 1.25^3":"0.984","Mono":"O","RMSE":"4.232","RMSE log":"0.170","Resolution":"640x192","Sq Rel":"0.649","absolute relative error":"0.091"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen-1","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split unsupervised","model":"Manydepth2-NF(M+640x192)","rank_in_archive_order":11,"of":55,"metrics":{"Delta < 1.25":"0.909","Delta < 1.25^2":"0.968","Delta < 1.25^3":"0.985","Mono":"O","RMSE":"4.246","RMSE log":"0.170","Resolution":"640x192","Sq Rel":"0.676","absolute relative error":"0.094"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2312.15268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15268"}},"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/kaichen-z/rad","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"listed":{"samples":9,"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":"912d199c3953a291","entry":"expected_mask","repo":"kaichen-z/rad","repo_kind":"listed","path":"src/rad_benchmark/dataset.py","file_url":"https://github.com/kaichen-z/rad/blob/HEAD/src/rad_benchmark/dataset.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":"912d199c3953a291"}},{"code_sha256_prefix":"4d8ce4241fb913a1","entry":"find_frame_image","repo":"kaichen-z/rad","repo_kind":"listed","path":"methods/reconstruction/prepare_splatpose.py","file_url":"https://github.com/kaichen-z/rad/blob/HEAD/methods/reconstruction/prepare_splatpose.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":"4d8ce4241fb913a1"}},{"code_sha256_prefix":"39fc6a86b2383324","entry":"image_files","repo":"kaichen-z/rad","repo_kind":"listed","path":"src/rad_benchmark/dataset.py","file_url":"https://github.com/kaichen-z/rad/blob/HEAD/src/rad_benchmark/dataset.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":"39fc6a86b2383324"}},{"code_sha256_prefix":"0e96095b79389d1f","entry":"main","repo":"kaichen-z/rad","repo_kind":"listed","path":"methods/adaclip/rad_dataset.py","file_url":"https://github.com/kaichen-z/rad/blob/HEAD/methods/adaclip/rad_dataset.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":"0e96095b79389d1f"}},{"code_sha256_prefix":"dbd2e7ce0cab8f36","entry":"make_datamodule","repo":"kaichen-z/rad","repo_kind":"listed","path":"src/rad_benchmark/anomalib.py","file_url":"https://github.com/kaichen-z/rad/blob/HEAD/src/rad_benchmark/anomalib.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":"dbd2e7ce0cab8f36"}},{"code_sha256_prefix":"5cda90a640730962","entry":"prepare_instance","repo":"kaichen-z/rad","repo_kind":"listed","path":"methods/reconstruction/prepare_splatpose.py","file_url":"https://github.com/kaichen-z/rad/blob/HEAD/methods/reconstruction/prepare_splatpose.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":"5cda90a640730962"}},{"code_sha256_prefix":"4e78f12d966e5c14","entry":"render_response_mask","repo":"kaichen-z/rad","repo_kind":"listed","path":"src/rad_benchmark/vlm.py","file_url":"https://github.com/kaichen-z/rad/blob/HEAD/src/rad_benchmark/vlm.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":"4e78f12d966e5c14"}},{"code_sha256_prefix":"17be5a566a64e5e8","entry":"responses_to_masks","repo":"kaichen-z/rad","repo_kind":"listed","path":"src/rad_benchmark/vlm.py","file_url":"https://github.com/kaichen-z/rad/blob/HEAD/src/rad_benchmark/vlm.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":"17be5a566a64e5e8"}},{"code_sha256_prefix":"1ea4186ada7a1f36","entry":"validate_instance","repo":"kaichen-z/rad","repo_kind":"listed","path":"src/rad_benchmark/dataset.py","file_url":"https://github.com/kaichen-z/rad/blob/HEAD/src/rad_benchmark/dataset.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":"1ea4186ada7a1f36"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}