{"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/depth-aware-cnn-for-rgb-d-segmentation","title":"Depth-aware CNN for RGB-D Segmentation","arxiv_id":"1803.06791","date":"2018-03-19","proceeding":"ECCV 2018 9","authors":["Weiyue Wang","Ulrich Neumann"],"abstract":"Convolutional neural networks (CNN) are limited by the lack of capability to\nhandle geometric information due to the fixed grid kernel structure. The\navailability of depth data enables progress in RGB-D semantic segmentation with\nCNNs. State-of-the-art methods either use depth as additional images or process\nspatial information in 3D volumes or point clouds. These methods suffer from\nhigh computation and memory cost. To address these issues, we present\nDepth-aware CNN by introducing two intuitive, flexible and effective\noperations: depth-aware convolution and depth-aware average pooling. By\nleveraging depth similarity between pixels in the process of information\npropagation, geometry is seamlessly incorporated into CNN. Without introducing\nany additional parameters, both operators can be easily integrated into\nexisting CNNs. Extensive experiments and ablation studies on challenging RGB-D\nsemantic segmentation benchmarks validate the effectiveness and flexibility of\nour approach.","url_abs":"http://arxiv.org/abs/1803.06791v1","url_pdf":"http://arxiv.org/pdf/1803.06791v1.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":"depth-aware-cnn-for-rgb-d-segmentation","repo_url":"https://github.com/laughtervv/DepthAwareCNN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"depth-aware-cnn-for-rgb-d-segmentation","repo_url":"https://github.com/aksh1501/DepthAware_CNN_edit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"depth-aware-cnn-for-rgb-d-segmentation","repo_url":"https://github.com/iriszero/DepthAwareCNNplus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"depth-aware-cnn-for-rgb-d-segmentation","repo_url":"https://github.com/virkay/DepthAwareCNN2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"thermal-image-segmentation","task_name":"Thermal Image Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"Depth-aware CNN","rank_in_archive_order":98,"of":121,"metrics":{"Mean IoU":"43.9%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-sun-rgbd","task":"Semantic Segmentation","dataset":"SUN-RGBD","model":"TokenFusion (S)","rank_in_archive_order":42,"of":44,"metrics":{"Mean IoU":"42.0%"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-stanford2d3d-rgbd","task":"Semantic Segmentation","dataset":"Stanford2D3D - RGBD","model":"Depth-aware CNN","rank_in_archive_order":6,"of":6,"metrics":{"Pixel Accuracy":"65.4","mAcc":"55.5","mIoU":"39.5"},"uses_additional_data":false},{"leaderboard":"/sota/thermal-image-segmentation-on-mfn-dataset","task":"Thermal Image Segmentation","dataset":"MFN Dataset","model":"Depth-aware CNN","rank_in_archive_order":46,"of":55,"metrics":{"mIOU":"46.1"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1803.06791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.06791"}},"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/virkay/DepthAwareCNN2","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/laughtervv/DepthAwareCNN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iriszero/DepthAwareCNNplus","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aksh1501/DepthAware_CNN_edit","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":10},"by_repo_kind":{"official":{"samples":8,"ran":1,"repositories":1},"listed":{"samples":3,"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":"098a8251265f82c2","entry":"uint82bin","repo":"laughtervv/DepthAwareCNN","repo_kind":"official","path":"utils/util.py","file_url":"https://github.com/laughtervv/DepthAwareCNN/blob/HEAD/utils/util.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"098a8251265f82c2"}},{"code_sha256_prefix":"aa4b1a72a86182e3","entry":"contiguous","repo":"aksh1501/DepthAware_CNN_edit","repo_kind":"listed","path":"utils/gradcheck.py","file_url":"https://github.com/aksh1501/DepthAware_CNN_edit/blob/HEAD/utils/gradcheck.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":"aa4b1a72a86182e3"}},{"code_sha256_prefix":"2550125e25acce91","entry":"create_model","repo":"laughtervv/DepthAwareCNN","repo_kind":"official","path":"models/models.py","file_url":"https://github.com/laughtervv/DepthAwareCNN/blob/HEAD/models/models.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":"2550125e25acce91"}},{"code_sha256_prefix":"8a7cda981e891b1b","entry":"cross_entropy2d","repo":"laughtervv/DepthAwareCNN","repo_kind":"official","path":"models/losses.py","file_url":"https://github.com/laughtervv/DepthAwareCNN/blob/HEAD/models/losses.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":"8a7cda981e891b1b"}},{"code_sha256_prefix":"72271df9d7f8f6ad","entry":"get_numerical_jacobian","repo":"aksh1501/DepthAware_CNN_edit","repo_kind":"listed","path":"utils/gradcheck.py","file_url":"https://github.com/aksh1501/DepthAware_CNN_edit/blob/HEAD/utils/gradcheck.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":"72271df9d7f8f6ad"}},{"code_sha256_prefix":"c47ae52360c6b10a","entry":"label_accuracy_score","repo":"laughtervv/DepthAwareCNN","repo_kind":"official","path":"utils/util.py","file_url":"https://github.com/laughtervv/DepthAwareCNN/blob/HEAD/utils/util.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":"c47ae52360c6b10a"}},{"code_sha256_prefix":"48d8d1e1855aa6dd","entry":"labelcolormap","repo":"laughtervv/DepthAwareCNN","repo_kind":"official","path":"utils/util.py","file_url":"https://github.com/laughtervv/DepthAwareCNN/blob/HEAD/utils/util.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":"48d8d1e1855aa6dd"}},{"code_sha256_prefix":"8c31f5f90a12d378","entry":"make_jacobian","repo":"aksh1501/DepthAware_CNN_edit","repo_kind":"listed","path":"utils/gradcheck.py","file_url":"https://github.com/aksh1501/DepthAware_CNN_edit/blob/HEAD/utils/gradcheck.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":"8c31f5f90a12d378"}},{"code_sha256_prefix":"b0ad13db5a53e1a2","entry":"make_layers","repo":"laughtervv/DepthAwareCNN","repo_kind":"official","path":"models/VGG_Deeplab.py","file_url":"https://github.com/laughtervv/DepthAwareCNN/blob/HEAD/models/VGG_Deeplab.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":"b0ad13db5a53e1a2"}},{"code_sha256_prefix":"b6bdfbe93eac1645","entry":"vgg16","repo":"laughtervv/DepthAwareCNN","repo_kind":"official","path":"models/VGG_Deeplab.py","file_url":"https://github.com/laughtervv/DepthAwareCNN/blob/HEAD/models/VGG_Deeplab.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":"b6bdfbe93eac1645"}},{"code_sha256_prefix":"fa8c10bd6c94939c","entry":"vgg16_bn","repo":"laughtervv/DepthAwareCNN","repo_kind":"official","path":"models/VGG_Deeplab.py","file_url":"https://github.com/laughtervv/DepthAwareCNN/blob/HEAD/models/VGG_Deeplab.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":"fa8c10bd6c94939c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}