{"url":"/sota/generative-3d-object-classification-on-1","task":{"name":"Generative 3D Object Classification","url":"/task/generative-3d-object-classification","note":null},"dataset":{"name":"Objaverse","url":"/dataset/objaverse"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"The task of generative 3D object classification involves prompting the model to generate the object type from its point cloud, distinguishing it from discriminative models that directly classify objects based on probability comparisons.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Objaverse (Average)","Objaverse (I)","Objaverse (C)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Objaverse (Average)":null,"Objaverse (I)":null,"Objaverse (C)":null}},"counts":{"rows":7,"rows_with_code":7,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"MiniGPT-3D","metrics":{"Objaverse (Average)":"60.25","Objaverse (C)":"60.50","Objaverse (I)":"60.00"},"uses_additional_data":false,"paper_date":"2024-05-02","paper":"/paper/minigpt-3d-efficiently-aligning-3d-point","paper_url":"https://arxiv.org/abs/2405.01413v1","paper_title":"MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors","code":"https://github.com/tangyuan96/minigpt-3d","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"ShapeLLM-7B","metrics":{"Objaverse (Average)":"54.50"},"uses_additional_data":false,"paper_date":"2024-02-27","paper":"/paper/shapellm-universal-3d-object-understanding","paper_url":"https://arxiv.org/abs/2402.17766v3","paper_title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","code":"https://github.com/qizekun/ShapeLLM","n_code_links":3,"syntology":{"n_ran":9,"n_unverified":8,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"PointLLM-13B v1.2","metrics":{"Objaverse (Average)":"54.00","Objaverse (C)":"51.50","Objaverse (I)":"56.50"},"uses_additional_data":false,"paper_date":"2023-08-31","paper":"/paper/pointllm-empowering-large-language-models-to","paper_url":"https://arxiv.org/abs/2308.16911v3","paper_title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","code":"https://github.com/openrobotlab/pointllm","n_code_links":3,"syntology":null},{"rank_in_archive_order":4,"model":"ShapeLLM-13B","metrics":{"Objaverse (Average)":"54.00"},"uses_additional_data":false,"paper_date":"2024-02-27","paper":"/paper/shapellm-universal-3d-object-understanding","paper_url":"https://arxiv.org/abs/2402.17766v3","paper_title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","code":"https://github.com/qizekun/ShapeLLM","n_code_links":3,"syntology":{"n_ran":9,"n_unverified":8,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"PointLLM-7B v1.2","metrics":{"Objaverse (Average)":" 53.00","Objaverse (C)":"51.00","Objaverse (I)":"55.00"},"uses_additional_data":false,"paper_date":"2023-08-31","paper":"/paper/pointllm-empowering-large-language-models-to","paper_url":"https://arxiv.org/abs/2308.16911v3","paper_title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","code":"https://github.com/openrobotlab/pointllm","n_code_links":3,"syntology":null},{"rank_in_archive_order":6,"model":"3D-LLM","metrics":{"Objaverse (Average)":"45.25","Objaverse (C)":"41.50","Objaverse (I)":"49.00"},"uses_additional_data":false,"paper_date":"2023-07-24","paper":"/paper/3d-llm-injecting-the-3d-world-into-large","paper_url":"https://arxiv.org/abs/2307.12981v1","paper_title":"3D-LLM: Injecting the 3D World into Large Language Models","code":"https://github.com/umass-foundation-model/3d-llm","n_code_links":5,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":10}},{"rank_in_archive_order":7,"model":"Point-Bind LLM","metrics":{"Objaverse (Average)":"5.25","Objaverse (C)":"4.50","Objaverse (I)":"6.00"},"uses_additional_data":false,"paper_date":"2023-09-01","paper":"/paper/point-bind-point-llm-aligning-point-cloud","paper_url":"https://arxiv.org/abs/2309.00615v1","paper_title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","code":"https://github.com/openrobotlab/pointllm","n_code_links":5,"syntology":{"n_ran":13,"n_unverified":7,"n_samples":20,"n_pointer_only_licence":7}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":4,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":27,"n_unverified":20,"n_samples":47,"n_pointer_only_licence":17,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":36,"n_unverified":28,"n_samples":64,"n_pointer_only_licence":17,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}