{"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/semantic-abstraction-open-world-3d-scene","title":"Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models","arxiv_id":"2207.11514","date":"2022-07-23","proceeding":null,"authors":["Huy Ha","Shuran Song"],"abstract":"We study open-world 3D scene understanding, a family of tasks that require agents to reason about their 3D environment with an open-set vocabulary and out-of-domain visual inputs - a critical skill for robots to operate in the unstructured 3D world. Towards this end, we propose Semantic Abstraction (SemAbs), a framework that equips 2D Vision-Language Models (VLMs) with new 3D spatial capabilities, while maintaining their zero-shot robustness. We achieve this abstraction using relevancy maps extracted from CLIP, and learn 3D spatial and geometric reasoning skills on top of those abstractions in a semantic-agnostic manner. We demonstrate the usefulness of SemAbs on two open-world 3D scene understanding tasks: 1) completing partially observed objects and 2) localizing hidden objects from language descriptions. Experiments show that SemAbs can generalize to novel vocabulary, materials/lighting, classes, and domains (i.e., real-world scans) from training on limited 3D synthetic data. Code and data is available at https://semantic-abstraction.cs.columbia.edu/","url_abs":"https://arxiv.org/abs/2207.11514v2","url_pdf":"https://arxiv.org/pdf/2207.11514v2.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":"semantic-abstraction-open-world-3d-scene","repo_url":"https://github.com/columbia-ai-robotics/semantic-abstraction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"scene-understanding","task_name":"Scene Understanding"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.11514","atlas_url":"https://app.syntology.ai/?focus=2207.11514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.11514"}},"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/columbia-ai-robotics/semantic-abstraction","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":14,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":18,"ran":15,"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":"c99fb7b9654ea364","entry":"act_layer","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"arm/network_utils.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/arm/network_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":true,"mcp_get_code":{"code_sha256":"c99fb7b9654ea364"}},{"code_sha256_prefix":"11714e67cd68342c","entry":"check_inside_receptacle","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"generate_thor_data.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/generate_thor_data.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":true,"mcp_get_code":{"code_sha256":"11714e67cd68342c"}},{"code_sha256_prefix":"f14e86248656890d","entry":"conv3d","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"unet3d.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/unet3d.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":true,"mcp_get_code":{"code_sha256":"f14e86248656890d"}},{"code_sha256_prefix":"23123534570bbc23","entry":"create_conv","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"unet3d.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/unet3d.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":true,"mcp_get_code":{"code_sha256":"23123534570bbc23"}},{"code_sha256_prefix":"a9a56fd2c94f4272","entry":"filter_pts_bounds","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"point_cloud.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/point_cloud.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":true,"mcp_get_code":{"code_sha256":"a9a56fd2c94f4272"}},{"code_sha256_prefix":"601919a9fac11376","entry":"get_datastructure","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"generate_relevancy.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/generate_relevancy.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":true,"mcp_get_code":{"code_sha256":"601919a9fac11376"}},{"code_sha256_prefix":"a417f67dfb52536a","entry":"get_pointcloud","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"point_cloud.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/point_cloud.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":true,"mcp_get_code":{"code_sha256":"a417f67dfb52536a"}},{"code_sha256_prefix":"cb35e06cffb77cfc","entry":"get_view_frustum","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"fusion.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/fusion.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":true,"mcp_get_code":{"code_sha256":"cb35e06cffb77cfc"}},{"code_sha256_prefix":"9ed9933be23b28a5","entry":"norm_layer1d","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"arm/network_utils.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/arm/network_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":true,"mcp_get_code":{"code_sha256":"9ed9933be23b28a5"}},{"code_sha256_prefix":"d0264b5831943fb9","entry":"norm_layer2d","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"arm/network_utils.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/arm/network_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":true,"mcp_get_code":{"code_sha256":"d0264b5831943fb9"}},{"code_sha256_prefix":"432a763e2bd52224","entry":"number_of_features_per_level","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"unet3d.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/unet3d.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"432a763e2bd52224"}},{"code_sha256_prefix":"0d62ec9279f07e05","entry":"parse_gt","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"generate_thor_data.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/generate_thor_data.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":true,"mcp_get_code":{"code_sha256":"0d62ec9279f07e05"}},{"code_sha256_prefix":"5e042598b503321c","entry":"plot_to_png","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"plot_utils.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/plot_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":true,"mcp_get_code":{"code_sha256":"5e042598b503321c"}},{"code_sha256_prefix":"dc7f3e9cf45d3d8b","entry":"rigid_transform","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"fusion.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/fusion.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":true,"mcp_get_code":{"code_sha256":"dc7f3e9cf45d3d8b"}},{"code_sha256_prefix":"2fe8a569ae92cf5d","entry":"transform_pointcloud","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"point_cloud.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/point_cloud.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":true,"mcp_get_code":{"code_sha256":"2fe8a569ae92cf5d"}},{"code_sha256_prefix":"bab82313e856d93a","entry":"deref_h5py","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/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":"bab82313e856d93a"}},{"code_sha256_prefix":"8ab1c21f0686b160","entry":"plot_pointcloud","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"plot_utils.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/plot_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":true,"mcp_get_code":{"code_sha256":"8ab1c21f0686b160"}},{"code_sha256_prefix":"d247ec33573d889a","entry":"process_receptacle_line","repo":"columbia-ai-robotics/semantic-abstraction","repo_kind":"official","path":"generate_thor_data.py","file_url":"https://github.com/columbia-ai-robotics/semantic-abstraction/blob/HEAD/generate_thor_data.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":"d247ec33573d889a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}