{"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/non-local-spatial-propagation-network-for","title":"Non-Local Spatial Propagation Network for Depth Completion","arxiv_id":"2007.10042","date":"2020-07-20","proceeding":"ECCV 2020 8","authors":["Jinsun Park","Kyungdon Joo","Zhe Hu","Chi-Kuei Liu","In So Kweon"],"abstract":"In this paper, we propose a robust and efficient end-to-end non-local spatial propagation network for depth completion. The proposed network takes RGB and sparse depth images as inputs and estimates non-local neighbors and their affinities of each pixel, as well as an initial depth map with pixel-wise confidences. The initial depth prediction is then iteratively refined by its confidence and non-local spatial propagation procedure based on the predicted non-local neighbors and corresponding affinities. Unlike previous algorithms that utilize fixed-local neighbors, the proposed algorithm effectively avoids irrelevant local neighbors and concentrates on relevant non-local neighbors during propagation. In addition, we introduce a learnable affinity normalization to better learn the affinity combinations compared to conventional methods. The proposed algorithm is inherently robust to the mixed-depth problem on depth boundaries, which is one of the major issues for existing depth estimation/completion algorithms. Experimental results on indoor and outdoor datasets demonstrate that the proposed algorithm is superior to conventional algorithms in terms of depth completion accuracy and robustness to the mixed-depth problem. Our implementation is publicly available on the project page.","url_abs":"https://arxiv.org/abs/2007.10042v1","url_pdf":"https://arxiv.org/pdf/2007.10042v1.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":"non-local-spatial-propagation-network-for","repo_url":"https://github.com/zzangjinsun/NLSPN_ECCV20","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"depth-completion","task_name":"Depth Completion"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"},{"task_slug":"stereo-lidar-fusion","task_name":"Stereo-LiDAR Fusion"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/depth-completion-on-kitti-depth-completion","task":"Depth Completion","dataset":"KITTI Depth Completion","model":"NLSPN","rank_in_archive_order":4,"of":16,"metrics":{"MAE":"199.59","RMSE":"741.68","Runtime [ms]":"220","iMAE":"0.84","iRMSE":"1.99"},"uses_additional_data":false},{"leaderboard":"/sota/depth-completion-on-nyu-depth-v2","task":"Depth Completion","dataset":"NYU-Depth V2","model":"NLSPN","rank_in_archive_order":1,"of":3,"metrics":{"REL":"0.012","RMSE":"0.092"},"uses_additional_data":false},{"leaderboard":"/sota/depth-completion-on-void","task":"Depth Completion","dataset":"VOID","model":"NLSPN","rank_in_archive_order":1,"of":6,"metrics":{"MAE":"26.736","RMSE":"79.121","iMAE":"12.703","iRMSE":"33.876"},"uses_additional_data":false},{"leaderboard":"/sota/stereo-lidar-fusion-on-kitti-depth-completion","task":"Stereo-LiDAR Fusion","dataset":"KITTI Depth Completion Validation","model":"NLSPN","rank_in_archive_order":5,"of":9,"metrics":{"RMSE":"771.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.10042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.10042"}},"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/zzangjinsun/NLSPN_ECCV20","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"ran":1,"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":"f8ca3cb40c015a0b","entry":"convert_str_to_num","repo":"zzangjinsun/NLSPN_ECCV20","repo_kind":"official","path":"src/utility.py","file_url":"https://github.com/zzangjinsun/NLSPN_ECCV20/blob/HEAD/src/utility.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":"f8ca3cb40c015a0b"}},{"code_sha256_prefix":"6cb043ab22719b0a","entry":"conv_bn_relu","repo":"zzangjinsun/NLSPN_ECCV20","repo_kind":"official","path":"src/model/common.py","file_url":"https://github.com/zzangjinsun/NLSPN_ECCV20/blob/HEAD/src/model/common.py","link_basis":"plan_row","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":"6cb043ab22719b0a"}},{"code_sha256_prefix":"d3f8a892fddc538a","entry":"get_resnet18","repo":"zzangjinsun/NLSPN_ECCV20","repo_kind":"official","path":"src/model/common.py","file_url":"https://github.com/zzangjinsun/NLSPN_ECCV20/blob/HEAD/src/model/common.py","link_basis":"plan_row","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":"d3f8a892fddc538a"}},{"code_sha256_prefix":"31c1784010ed8209","entry":"get_resnet34","repo":"zzangjinsun/NLSPN_ECCV20","repo_kind":"official","path":"src/model/common.py","file_url":"https://github.com/zzangjinsun/NLSPN_ECCV20/blob/HEAD/src/model/common.py","link_basis":"plan_row","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":"31c1784010ed8209"}},{"code_sha256_prefix":"ac1d9fa412ad7df0","entry":"make_optimizer_scheduler","repo":"zzangjinsun/NLSPN_ECCV20","repo_kind":"official","path":"src/utility.py","file_url":"https://github.com/zzangjinsun/NLSPN_ECCV20/blob/HEAD/src/utility.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":"ac1d9fa412ad7df0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}