{"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/3d-to-2d-distillation-for-indoor-scene","title":"3D-to-2D Distillation for Indoor Scene Parsing","arxiv_id":"2104.02243","date":"2021-04-06","proceeding":"CVPR 2021 1","authors":["Zhengzhe Liu","Xiaojuan Qi","Chi-Wing Fu"],"abstract":"Indoor scene semantic parsing from RGB images is very challenging due to occlusions, object distortion, and viewpoint variations. Going beyond prior works that leverage geometry information, typically paired depth maps, we present a new approach, a 3D-to-2D distillation framework, that enables us to leverage 3D features extracted from large-scale 3D data repository (e.g., ScanNet-v2) to enhance 2D features extracted from RGB images. Our work has three novel contributions. First, we distill 3D knowledge from a pretrained 3D network to supervise a 2D network to learn simulated 3D features from 2D features during the training, so the 2D network can infer without requiring 3D data. Second, we design a two-stage dimension normalization scheme to calibrate the 2D and 3D features for better integration. Third, we design a semantic-aware adversarial training model to extend our framework for training with unpaired 3D data. Extensive experiments on various datasets, ScanNet-V2, S3DIS, and NYU-v2, demonstrate the superiority of our approach. Also, experimental results show that our 3D-to-2D distillation improves the model generalization.","url_abs":"https://arxiv.org/abs/2104.02243v2","url_pdf":"https://arxiv.org/pdf/2104.02243v2.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":"3d-to-2d-distillation-for-indoor-scene","repo_url":"https://github.com/liuzhengzhe/3D-to-2D-Distillation-for-Indoor-Scene-Parsing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"scene-parsing","task_name":"Scene Parsing"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.02243","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.02243"}},"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/liuzhengzhe/3D-to-2D-Distillation-for-Indoor-Scene-Parsing","reach":null}],"summary":{"ran":1,"ran_draft_wrong":3,"unverified":3},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"9db6118db9412494","entry":"ResNet","repo":"liuzhengzhe/3D-to-2D-Distillation-for-Indoor-Scene-Parsing","repo_kind":"official","path":"3d-2d-distillation/model/psanet.py","file_url":"https://github.com/liuzhengzhe/3D-to-2D-Distillation-for-Indoor-Scene-Parsing/blob/HEAD/3d-2d-distillation/model/psanet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9db6118db9412494"}},{"code_sha256_prefix":"764fd2589f954854","entry":"resnet101","repo":"liuzhengzhe/3D-to-2D-Distillation-for-Indoor-Scene-Parsing","repo_kind":"official","path":"3d-2d-distillation/model/psanet.py","file_url":"https://github.com/liuzhengzhe/3D-to-2D-Distillation-for-Indoor-Scene-Parsing/blob/HEAD/3d-2d-distillation/model/psanet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"764fd2589f954854"}},{"code_sha256_prefix":"5d6c490fe9c23250","entry":"resnet152","repo":"liuzhengzhe/3D-to-2D-Distillation-for-Indoor-Scene-Parsing","repo_kind":"official","path":"3d-2d-distillation/model/psanet.py","file_url":"https://github.com/liuzhengzhe/3D-to-2D-Distillation-for-Indoor-Scene-Parsing/blob/HEAD/3d-2d-distillation/model/psanet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5d6c490fe9c23250"}},{"code_sha256_prefix":"9dba5bf3c2e36b81","entry":"resnet50","repo":"liuzhengzhe/3D-to-2D-Distillation-for-Indoor-Scene-Parsing","repo_kind":"official","path":"3d-2d-distillation/model/psanet.py","file_url":"https://github.com/liuzhengzhe/3D-to-2D-Distillation-for-Indoor-Scene-Parsing/blob/HEAD/3d-2d-distillation/model/psanet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9dba5bf3c2e36b81"}},{"code_sha256_prefix":"49550c4e8f8fc788","entry":"PSA","repo":"liuzhengzhe/3D-to-2D-Distillation-for-Indoor-Scene-Parsing","repo_kind":"official","path":"3d-2d-distillation/model/psanet.py","file_url":"https://github.com/liuzhengzhe/3D-to-2D-Distillation-for-Indoor-Scene-Parsing/blob/HEAD/3d-2d-distillation/model/psanet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"49550c4e8f8fc788"}},{"code_sha256_prefix":"73a8920d7c78bd80","entry":"PSANet","repo":"liuzhengzhe/3D-to-2D-Distillation-for-Indoor-Scene-Parsing","repo_kind":"official","path":"3d-2d-distillation/model/psanet.py","file_url":"https://github.com/liuzhengzhe/3D-to-2D-Distillation-for-Indoor-Scene-Parsing/blob/HEAD/3d-2d-distillation/model/psanet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"73a8920d7c78bd80"}},{"code_sha256_prefix":"04a42232bb1c7453","entry":"psa_mask","repo":"liuzhengzhe/3D-to-2D-Distillation-for-Indoor-Scene-Parsing","repo_kind":"official","path":"3d-2d-distillation/model/psanet.py","file_url":"https://github.com/liuzhengzhe/3D-to-2D-Distillation-for-Indoor-Scene-Parsing/blob/HEAD/3d-2d-distillation/model/psanet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"04a42232bb1c7453"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}