{"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/shapellm-universal-3d-object-understanding","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","arxiv_id":"2402.17766","date":"2024-02-27","proceeding":null,"authors":["Zekun Qi","Runpei Dong","Shaochen Zhang","Haoran Geng","Chunrui Han","Zheng Ge","Li Yi","Kaisheng Ma"],"abstract":"This paper presents ShapeLLM, the first 3D Multimodal Large Language Model (LLM) designed for embodied interaction, exploring a universal 3D object understanding with 3D point clouds and languages. ShapeLLM is built upon an improved 3D encoder by extending ReCon to ReCon++ that benefits from multi-view image distillation for enhanced geometry understanding. By utilizing ReCon++ as the 3D point cloud input encoder for LLMs, ShapeLLM is trained on constructed instruction-following data and tested on our newly human-curated benchmark, 3D MM-Vet. ReCon++ and ShapeLLM achieve state-of-the-art performance in 3D geometry understanding and language-unified 3D interaction tasks, such as embodied visual grounding. Project page: https://qizekun.github.io/shapellm/","url_abs":"https://arxiv.org/abs/2402.17766v3","url_pdf":"https://arxiv.org/pdf/2402.17766v3.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":"shapellm-universal-3d-object-understanding","repo_url":"https://github.com/qizekun/ShapeLLM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"shapellm-universal-3d-object-understanding","repo_url":"https://github.com/qizekun/ReCon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"shapellm-universal-3d-object-understanding","repo_url":"https://github.com/runpeidong/act","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-object-captioning","task_name":"3D Object Captioning"},{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"3d-point-cloud-linear-classification","task_name":"3D Point Cloud Linear Classification"},{"task_slug":"3d-question-answering-3d-qa","task_name":"3D Question Answering (3D-QA)"},{"task_slug":"3d-geometry","task_name":"3D geometry"},{"task_slug":"few-shot-3d-point-cloud-classification","task_name":"Few-Shot 3D Point Cloud Classification"},{"task_slug":"generative-3d-object-classification","task_name":"Generative 3D Object Classification"},{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":null,"task_name":"MM-Vet"},{"task_slug":"multimodal-large-language-model","task_name":"Multimodal Large Language Model"},{"task_slug":"object","task_name":"Object"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"},{"task_slug":"zero-shot-transfer-3d-point-cloud","task_name":"Zero-Shot Transfer 3D Point Cloud Classification"},{"task_slug":"zero-shot-3d-classification","task_name":"Zero-shot 3D classification"}],"methods":[],"datasets_introduced":[{"slug":"3d-mm-vet","name":"3D MM-Vet","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-captioning-on-objaverse-1","task":"3D Object Captioning","dataset":"Objaverse","model":"ShapeLLM-13B","rank_in_archive_order":2,"of":6,"metrics":{" Sentence-BERT":"48.52","GPT-4":"48.94","SimCSE":"49.98"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-captioning-on-objaverse-1","task":"3D Object Captioning","dataset":"Objaverse","model":"ShapeLLM-7B","rank_in_archive_order":4,"of":6,"metrics":{" Sentence-BERT":"48.20","GPT-4":"46.92","SimCSE":"49.23"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"ReCon++","rank_in_archive_order":3,"of":111,"metrics":{"Overall Accuracy":"95.0"},"uses_additional_data":true},{"leaderboard":"/sota/3d-point-cloud-classification-on-scanobjectnn","task":"3D Point Cloud Classification","dataset":"ScanObjectNN","model":"ReCon++","rank_in_archive_order":5,"of":77,"metrics":{"OBJ-BG (OA)":"98.80","OBJ-ONLY (OA)":"97.59","Overall Accuracy":"95.25"},"uses_additional_data":true},{"leaderboard":"/sota/3d-point-cloud-linear-classification-on","task":"3D Point Cloud Linear Classification","dataset":"ModelNet40","model":"ReCon++","rank_in_archive_order":2,"of":20,"metrics":{"Overall Accuracy":"93.6"},"uses_additional_data":false},{"leaderboard":"/sota/3d-question-answering-3d-qa-on-3d-mm-vet","task":"3D Question Answering (3D-QA)","dataset":"3D MM-Vet","model":"ShapeLLM-13B","rank_in_archive_order":1,"of":5,"metrics":{"Overall Accuracy":"53.1"},"uses_additional_data":false},{"leaderboard":"/sota/3d-question-answering-3d-qa-on-3d-mm-vet","task":"3D Question Answering (3D-QA)","dataset":"3D MM-Vet","model":"ShapeLLM-7B","rank_in_archive_order":2,"of":5,"metrics":{"Overall Accuracy":"47.4"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-3","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 10-way (10-shot)","model":"ReCon++","rank_in_archive_order":2,"of":31,"metrics":{"Overall Accuracy":"94.5","Standard Deviation":"4.1"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-4","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 10-way (20-shot)","model":"ReCon++","rank_in_archive_order":1,"of":31,"metrics":{"Overall Accuracy":"96.5","Standard Deviation":"3.0"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-1","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 5-way (10-shot)","model":"ReCon++","rank_in_archive_order":2,"of":30,"metrics":{"Overall Accuracy":"98.0","Standard Deviation":"2.3"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-2","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 5-way (20-shot)","model":"ReCon++","rank_in_archive_order":1,"of":30,"metrics":{"Overall Accuracy":"99.5","Standard Deviation":"0.8"},"uses_additional_data":true},{"leaderboard":"/sota/generative-3d-object-classification-on-2","task":"Generative 3D Object Classification","dataset":"ModelNet40","model":"ShapeLLM-7B","rank_in_archive_order":2,"of":6,"metrics":{"ModelNet40 (Average)":"53.08"},"uses_additional_data":false},{"leaderboard":"/sota/generative-3d-object-classification-on-2","task":"Generative 3D Object Classification","dataset":"ModelNet40","model":"ShapeLLM-13B","rank_in_archive_order":3,"of":6,"metrics":{"ModelNet40 (Average)":"52.96"},"uses_additional_data":false},{"leaderboard":"/sota/generative-3d-object-classification-on-1","task":"Generative 3D Object Classification","dataset":"Objaverse","model":"ShapeLLM-7B","rank_in_archive_order":2,"of":7,"metrics":{"Objaverse (Average)":"54.50"},"uses_additional_data":false},{"leaderboard":"/sota/generative-3d-object-classification-on-1","task":"Generative 3D Object Classification","dataset":"Objaverse","model":"ShapeLLM-13B","rank_in_archive_order":4,"of":7,"metrics":{"Objaverse (Average)":"54.00"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-3d-point-cloud","task":"Zero-Shot Transfer 3D Point Cloud Classification","dataset":"ModelNet40","model":"ReCon++","rank_in_archive_order":3,"of":16,"metrics":{"Accuracy (%)":"87.3"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-transfer-3d-point-cloud-2","task":"Zero-Shot Transfer 3D Point Cloud Classification","dataset":"ScanObjectNN","model":"ReCon++","rank_in_archive_order":1,"of":10,"metrics":{"OBJ_ONLY Accuracy(%)":"65.4"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.17766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17766"}},"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/qizekun/ReCon","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qizekun/ShapeLLM","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/runpeidong/act","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":4,"ran":3,"ran_violates":1,"ran_honours":1,"unverified":8},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":15,"ran":7,"repositories":2}},"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":"98f385d847636a3e","entry":"basic_clean","repo":"qizekun/ReCon","repo_kind":"listed","path":"clip/simple_tokenizer.py","file_url":"https://github.com/qizekun/ReCon/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"10442b2d555aff2d","entry":"build_2d_sincos_posemb","repo":"runpeidong/act","repo_kind":"listed","path":"utils/transformer_layers.py","file_url":"https://github.com/runpeidong/act/blob/HEAD/utils/transformer_layers.py","link_basis":"first_harvest_node","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":"10442b2d555aff2d"}},{"code_sha256_prefix":"6a27d2ea085ab083","entry":"get_iou","repo":"qizekun/ShapeLLM","repo_kind":"official","path":"llava/eval/eval_gapartnet.py","file_url":"https://github.com/qizekun/ShapeLLM/blob/HEAD/llava/eval/eval_gapartnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6a27d2ea085ab083"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"qizekun/ReCon","repo_kind":"listed","path":"clip/simple_tokenizer.py","file_url":"https://github.com/qizekun/ReCon/blob/HEAD/clip/simple_tokenizer.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":"d919ae32e5e4e616"}},{"code_sha256_prefix":"6ba8cee9f5daea41","entry":"pair","repo":"runpeidong/act","repo_kind":"listed","path":"utils/transformer_layers.py","file_url":"https://github.com/runpeidong/act/blob/HEAD/utils/transformer_layers.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ba8cee9f5daea41"}},{"code_sha256_prefix":"4783fbece52f500e","entry":"pc_normalize","repo":"qizekun/ReCon","repo_kind":"listed","path":"datasets/ModelNetDataset.py","file_url":"https://github.com/qizekun/ReCon/blob/HEAD/datasets/ModelNetDataset.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4783fbece52f500e"}},{"code_sha256_prefix":"f6148d58020c40ae","entry":"pc_normalize","repo":"qizekun/ShapeLLM","repo_kind":"official","path":"ReConV2/datasets/ModelNetDataset.py","file_url":"https://github.com/qizekun/ShapeLLM/blob/HEAD/ReConV2/datasets/ModelNetDataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f6148d58020c40ae"}},{"code_sha256_prefix":"74c3fe06cea2f553","entry":"square_distance","repo":"qizekun/ReCon","repo_kind":"listed","path":"segmentation/pointnet_util.py","file_url":"https://github.com/qizekun/ReCon/blob/HEAD/segmentation/pointnet_util.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"74c3fe06cea2f553"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"qizekun/ReCon","repo_kind":"listed","path":"clip/simple_tokenizer.py","file_url":"https://github.com/qizekun/ReCon/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"d996b25c2413180a","entry":"build_model","repo":"qizekun/ReCon","repo_kind":"listed","path":"clip/model.py","file_url":"https://github.com/qizekun/ReCon/blob/HEAD/clip/model.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":"d996b25c2413180a"}},{"code_sha256_prefix":"73cecca9f3575f09","entry":"concat_all_gather","repo":"runpeidong/act","repo_kind":"listed","path":"models/act.py","file_url":"https://github.com/runpeidong/act/blob/HEAD/models/act.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":"73cecca9f3575f09"}},{"code_sha256_prefix":"f80066a00e7156a2","entry":"farthest_point_sample","repo":"qizekun/ReCon","repo_kind":"listed","path":"datasets/ModelNetDataset.py","file_url":"https://github.com/qizekun/ReCon/blob/HEAD/datasets/ModelNetDataset.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":"f80066a00e7156a2"}},{"code_sha256_prefix":"55397203c1d5dac1","entry":"knn_point","repo":"runpeidong/act","repo_kind":"listed","path":"models/dvae.py","file_url":"https://github.com/runpeidong/act/blob/HEAD/models/dvae.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":"55397203c1d5dac1"}},{"code_sha256_prefix":"f6f30e41636ae569","entry":"load","repo":"qizekun/ReCon","repo_kind":"listed","path":"clip/clip.py","file_url":"https://github.com/qizekun/ReCon/blob/HEAD/clip/clip.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":"f6f30e41636ae569"}},{"code_sha256_prefix":"6ddec81b1d23c787","entry":"square_distance","repo":"runpeidong/act","repo_kind":"listed","path":"models/dvae.py","file_url":"https://github.com/runpeidong/act/blob/HEAD/models/dvae.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":"6ddec81b1d23c787"}},{"code_sha256_prefix":"b1227ddb721e2999","entry":"timeit","repo":"qizekun/ReCon","repo_kind":"listed","path":"segmentation/pointnet_util.py","file_url":"https://github.com/qizekun/ReCon/blob/HEAD/segmentation/pointnet_util.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":"b1227ddb721e2999"}},{"code_sha256_prefix":"5436174f8c0e64e0","entry":"trunc_normal_","repo":"runpeidong/act","repo_kind":"listed","path":"utils/transformer_layers.py","file_url":"https://github.com/runpeidong/act/blob/HEAD/utils/transformer_layers.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":"5436174f8c0e64e0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}