{"url":"/task/generative-3d-object-classification","name":"Generative 3D Object Classification","slug":"generative-3d-object-classification","description_markdown":"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.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":5,"papers_with_code":5,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/generative-3d-object-classification-on-1","slug":"generative-3d-object-classification-on-1","dataset":"Objaverse","dataset_url":"/dataset/objaverse","rows_in_archive":7,"metrics":["Objaverse (Average)","Objaverse (I)","Objaverse (C)"],"first_row_in_archive_order":{"model":"MiniGPT-3D","paper_title":"MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors","paper_url":"/paper/minigpt-3d-efficiently-aligning-3d-point","paper_date":"2024-05-02","arxiv_id":"2405.01413","code_links":[{"title":"tangyuan96/minigpt-3d","url":"https://github.com/tangyuan96/minigpt-3d"}],"syntology":null}},{"leaderboard":"/sota/generative-3d-object-classification-on-2","slug":"generative-3d-object-classification-on-2","dataset":"ModelNet40","dataset_url":"/dataset/modelnet","rows_in_archive":6,"metrics":["ModelNet40 (Average)","ModelNet40 (I)","ModelNet40 (C)"],"first_row_in_archive_order":{"model":"MiniGPT-3D","paper_title":"MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors","paper_url":"/paper/minigpt-3d-efficiently-aligning-3d-point","paper_date":"2024-05-02","arxiv_id":"2405.01413","code_links":[{"title":"tangyuan96/minigpt-3d","url":"https://github.com/tangyuan96/minigpt-3d"}],"syntology":null}}],"datasets":[{"url":"/dataset/modelnet","name":"ModelNet","full_name":"","num_papers_in_archive":1406},{"url":"/dataset/objaverse","name":"Objaverse","full_name":"","num_papers_in_archive":393}],"subtasks":[],"parent_tasks":[{"url":"/task/3d-object-classification","name":"3D Object Classification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":5,"of":5,"tagged_in_all":5,"items":[{"url":"/paper/point-bind-point-llm-aligning-point-cloud","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","date":"2023-09-01","arxiv_id":"2309.00615","repositories_listed":5,"syntology":{"n":20,"n_ran":13,"n_unverified":7,"n_pointer_only":7}},{"url":"/paper/3d-llm-injecting-the-3d-world-into-large","title":"3D-LLM: Injecting the 3D World into Large Language Models","date":"2023-07-24","arxiv_id":"2307.12981","repositories_listed":5,"syntology":{"n":10,"n_ran":5,"n_unverified":5,"n_pointer_only":10}},{"url":"/paper/shapellm-universal-3d-object-understanding","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","date":"2024-02-27","arxiv_id":"2402.17766","repositories_listed":3,"syntology":{"n":17,"n_ran":9,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/pointllm-empowering-large-language-models-to","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","date":"2023-08-31","arxiv_id":"2308.16911","repositories_listed":3,"syntology":null},{"url":"/paper/minigpt-3d-efficiently-aligning-3d-point","title":"MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors","date":"2024-05-02","arxiv_id":"2405.01413","repositories_listed":1,"syntology":null}],"syntology_records":3,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}