{"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/openshape-scaling-up-3d-shape-representation-1","title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","arxiv_id":"2305.10764","date":"2023-05-18","proceeding":"NeurIPS 2023 11","authors":["Minghua Liu","Ruoxi Shi","Kaiming Kuang","Yinhao Zhu","Xuanlin Li","Shizhong Han","Hong Cai","Fatih Porikli","Hao Su"],"abstract":"We introduce OpenShape, a method for learning multi-modal joint representations of text, image, and point clouds. We adopt the commonly used multi-modal contrastive learning framework for representation alignment, but with a specific focus on scaling up 3D representations to enable open-world 3D shape understanding. To achieve this, we scale up training data by ensembling multiple 3D datasets and propose several strategies to automatically filter and enrich noisy text descriptions. We also explore and compare strategies for scaling 3D backbone networks and introduce a novel hard negative mining module for more efficient training. We evaluate OpenShape on zero-shot 3D classification benchmarks and demonstrate its superior capabilities for open-world recognition. Specifically, OpenShape achieves a zero-shot accuracy of 46.8% on the 1,156-category Objaverse-LVIS benchmark, compared to less than 10% for existing methods. OpenShape also achieves an accuracy of 85.3% on ModelNet40, outperforming previous zero-shot baseline methods by 20% and performing on par with some fully-supervised methods. Furthermore, we show that our learned embeddings encode a wide range of visual and semantic concepts (e.g., subcategories, color, shape, style) and facilitate fine-grained text-3D and image-3D interactions. Due to their alignment with CLIP embeddings, our learned shape representations can also be integrated with off-the-shelf CLIP-based models for various applications, such as point cloud captioning and point cloud-conditioned image generation.","url_abs":"https://arxiv.org/abs/2305.10764v2","url_pdf":"https://arxiv.org/pdf/2305.10764v2.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":"openshape-scaling-up-3d-shape-representation-1","repo_url":"https://github.com/Colin97/OpenShape_code","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-classification","task_name":"3D Classification"},{"task_slug":"3d-shape-representation","task_name":"3D Shape Representation"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"zero-shot-transfer-3d-point-cloud","task_name":"Zero-Shot Transfer 3D Point Cloud Classification"},{"task_slug":"zero-shot-3d-point-cloud-classification","task_name":"Zero-shot 3D Point Cloud Classification"},{"task_slug":"zero-shot-3d-classification","task_name":"Zero-shot 3D classification"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-transfer-3d-point-cloud","task":"Zero-Shot Transfer 3D Point Cloud Classification","dataset":"ModelNet40","model":"OpenShape-PointBERT","rank_in_archive_order":7,"of":16,"metrics":{"Accuracy (%)":"85.3"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-transfer-3d-point-cloud","task":"Zero-Shot Transfer 3D Point Cloud Classification","dataset":"ModelNet40","model":"OpenShape-SparseConv","rank_in_archive_order":9,"of":16,"metrics":{"Accuracy (%)":"83.4"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.10764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10764"}},"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/Colin97/OpenShape_code","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":7},"by_repo_kind":{"listed":{"samples":7,"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":"148ffcae3506e52b","entry":"download_object","repo":"Colin97/OpenShape_code","repo_kind":"listed","path":"render_single_glb.py","file_url":"https://github.com/Colin97/OpenShape_code/blob/HEAD/render_single_glb.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"148ffcae3506e52b"}},{"code_sha256_prefix":"39cc8b0570b593bf","entry":"extract_clip_feat","repo":"Colin97/OpenShape_code","repo_kind":"listed","path":"src/extract_lvis_feat_ulip.py","file_url":"https://github.com/Colin97/OpenShape_code/blob/HEAD/src/extract_lvis_feat_ulip.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"39cc8b0570b593bf"}},{"code_sha256_prefix":"179cbecb2cbf9048","entry":"generate_prompts","repo":"Colin97/OpenShape_code","repo_kind":"listed","path":"src/extract_lvis_feat_ulip.py","file_url":"https://github.com/Colin97/OpenShape_code/blob/HEAD/src/extract_lvis_feat_ulip.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"179cbecb2cbf9048"}},{"code_sha256_prefix":"460808fbce44a8d8","entry":"load_file","repo":"Colin97/OpenShape_code","repo_kind":"listed","path":"src/models/Minkowski_resnet.py","file_url":"https://github.com/Colin97/OpenShape_code/blob/HEAD/src/models/Minkowski_resnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"460808fbce44a8d8"}},{"code_sha256_prefix":"6b8de911693ef6b0","entry":"make","repo":"Colin97/OpenShape_code","repo_kind":"listed","path":"src/models/pointmlp.py","file_url":"https://github.com/Colin97/OpenShape_code/blob/HEAD/src/models/pointmlp.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6b8de911693ef6b0"}},{"code_sha256_prefix":"7143f4924679ba89","entry":"parse_args","repo":"Colin97/OpenShape_code","repo_kind":"listed","path":"src/param.py","file_url":"https://github.com/Colin97/OpenShape_code/blob/HEAD/src/param.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7143f4924679ba89"}},{"code_sha256_prefix":"e33e634b676ccbf7","entry":"sample_camera_loc","repo":"Colin97/OpenShape_code","repo_kind":"listed","path":"render_single_glb.py","file_url":"https://github.com/Colin97/OpenShape_code/blob/HEAD/render_single_glb.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e33e634b676ccbf7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}