{"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/new-crfs-neural-window-fully-connected-crfs-1","title":"NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation","arxiv_id":"2203.01502","date":"2022-03-03","proceeding":"CVPR 2022 3","authors":["Weihao Yuan","Xiaodong Gu","Zuozhuo Dai","Siyu Zhu","Ping Tan"],"abstract":"Estimating the accurate depth from a single image is challenging since it is inherently ambiguous and ill-posed. While recent works design increasingly complicated and powerful networks to directly regress the depth map, we take the path of CRFs optimization. Due to the expensive computation, CRFs are usually performed between neighborhoods rather than the whole graph. To leverage the potential of fully-connected CRFs, we split the input into windows and perform the FC-CRFs optimization within each window, which reduces the computation complexity and makes FC-CRFs feasible. To better capture the relationships between nodes in the graph, we exploit the multi-head attention mechanism to compute a multi-head potential function, which is fed to the networks to output an optimized depth map. Then we build a bottom-up-top-down structure, where this neural window FC-CRFs module serves as the decoder, and a vision transformer serves as the encoder. The experiments demonstrate that our method significantly improves the performance across all metrics on both the KITTI and NYUv2 datasets, compared to previous methods. Furthermore, the proposed method can be directly applied to panorama images and outperforms all previous panorama methods on the MatterPort3D dataset. Project page: https://weihaosky.github.io/newcrfs.","url_abs":"https://arxiv.org/abs/2203.01502v2","url_pdf":"https://arxiv.org/pdf/2203.01502v2.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":"new-crfs-neural-window-fully-connected-crfs-1","repo_url":"https://github.com/aliyun/NeWCRFs","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split","model":"NeWCRFs","rank_in_archive_order":27,"of":79,"metrics":{"Delta < 1.25":"0.974","Delta < 1.25^2":"0.997","Delta < 1.25^3":"0.999","RMSE":"2.129","RMSE log":"0.079","Sq Rel":"0.155","absolute relative error":"0.052"},"uses_additional_data":true},{"leaderboard":"/sota/monocular-depth-estimation-on-matterport3d","task":"Monocular Depth Estimation","dataset":"Matterport3D","model":"NeWCRFs","rank_in_archive_order":1,"of":1,"metrics":{"Delta < 1.25":"0.9376","Delta < 1.25^2":"0.9812","Delta < 1.25^3":"0.9933","RMSE":"0.4279","absolute error":"0.197","absolute relative error":"0.0793"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-nyu-depth-v2","task":"Monocular Depth Estimation","dataset":"NYU-Depth V2","model":"NeWCRFs","rank_in_archive_order":43,"of":85,"metrics":{"Delta < 1.25":"0.922","Delta < 1.25^2":"0.992","Delta < 1.25^3":"0.998","RMSE":"0.334","absolute relative error":"0.095","log 10":"0.041"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.01502","atlas_url":"https://app.syntology.ai/?focus=2203.01502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.01502"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/aliyun/NeWCRFs","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran_honours":1,"ran":3,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":10,"ran":6,"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":10,"samples":[{"code_sha256_prefix":"144d10b49baeb8a6","entry":"window_partition","repo":"aliyun/NeWCRFs","repo_kind":"official","path":"newcrfs/networks/newcrf_layers.py","file_url":"https://github.com/aliyun/NeWCRFs/blob/HEAD/newcrfs/networks/newcrf_layers.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"144d10b49baeb8a6"}},{"code_sha256_prefix":"050c56fb7282eb88","entry":"get_num_lines","repo":"aliyun/NeWCRFs","repo_kind":"official","path":"newcrfs/utils.py","file_url":"https://github.com/aliyun/NeWCRFs/blob/HEAD/newcrfs/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"050c56fb7282eb88"}},{"code_sha256_prefix":"8a05ea4d5e917bf4","entry":"normalize_result","repo":"aliyun/NeWCRFs","repo_kind":"official","path":"newcrfs/utils.py","file_url":"https://github.com/aliyun/NeWCRFs/blob/HEAD/newcrfs/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":false,"mcp_get_code":{"code_sha256":"8a05ea4d5e917bf4"}},{"code_sha256_prefix":"ea623328271af85a","entry":"preprocessing_transforms","repo":"aliyun/NeWCRFs","repo_kind":"official","path":"newcrfs/dataloaders/dataloader.py","file_url":"https://github.com/aliyun/NeWCRFs/blob/HEAD/newcrfs/dataloaders/dataloader.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":false,"mcp_get_code":{"code_sha256":"ea623328271af85a"}},{"code_sha256_prefix":"35e6bae6a3fe0669","entry":"upsample","repo":"aliyun/NeWCRFs","repo_kind":"official","path":"newcrfs/networks/NewCRFDepth.py","file_url":"https://github.com/aliyun/NeWCRFs/blob/HEAD/newcrfs/networks/NewCRFDepth.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":false,"mcp_get_code":{"code_sha256":"35e6bae6a3fe0669"}},{"code_sha256_prefix":"61bf152e6a42a184","entry":"window_reverse","repo":"aliyun/NeWCRFs","repo_kind":"official","path":"newcrfs/networks/newcrf_layers.py","file_url":"https://github.com/aliyun/NeWCRFs/blob/HEAD/newcrfs/networks/newcrf_layers.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"61bf152e6a42a184"}},{"code_sha256_prefix":"9999af2cf9c1b6bb","entry":"colorize","repo":"aliyun/NeWCRFs","repo_kind":"official","path":"newcrfs/utils.py","file_url":"https://github.com/aliyun/NeWCRFs/blob/HEAD/newcrfs/utils.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":false,"mcp_get_code":{"code_sha256":"9999af2cf9c1b6bb"}},{"code_sha256_prefix":"9b9dd29ad0d626a0","entry":"is_module_wrapper","repo":"aliyun/NeWCRFs","repo_kind":"official","path":"newcrfs/networks/newcrf_utils.py","file_url":"https://github.com/aliyun/NeWCRFs/blob/HEAD/newcrfs/networks/newcrf_utils.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":false,"mcp_get_code":{"code_sha256":"9b9dd29ad0d626a0"}},{"code_sha256_prefix":"92dad73ee855852f","entry":"load_url_dist","repo":"aliyun/NeWCRFs","repo_kind":"official","path":"newcrfs/networks/newcrf_utils.py","file_url":"https://github.com/aliyun/NeWCRFs/blob/HEAD/newcrfs/networks/newcrf_utils.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":false,"mcp_get_code":{"code_sha256":"92dad73ee855852f"}},{"code_sha256_prefix":"9012d3fdd4cbaea1","entry":"resize","repo":"aliyun/NeWCRFs","repo_kind":"official","path":"newcrfs/networks/newcrf_utils.py","file_url":"https://github.com/aliyun/NeWCRFs/blob/HEAD/newcrfs/networks/newcrf_utils.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":false,"mcp_get_code":{"code_sha256":"9012d3fdd4cbaea1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}