{"url":"/task/3d-object-captioning","name":"3D Object Captioning","slug":"3d-object-captioning","description_markdown":"3D object captioning involves generating a natural language description of an object, given its point cloud representation.","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":7,"papers_with_code":6,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":0},"benchmarks":[{"leaderboard":"/sota/3d-object-captioning-on-objaverse-1","slug":"3d-object-captioning-on-objaverse-1","dataset":"Objaverse","dataset_url":"/dataset/objaverse","rows_in_archive":6,"metrics":["GPT-4"," Sentence-BERT","SimCSE","Precision","Correctness","Hallucination"],"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/objaverse","name":"Objaverse","full_name":"","num_papers_in_archive":393},{"url":"/dataset/tumtraffic-videoqa","name":"TUMTraffic-VideoQA","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":6,"of":6,"tagged_in_all":7,"items":[{"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/marvel-40m-multi-level-visual-elaboration-for","title":"MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation","date":"2024-11-26","arxiv_id":"2411.17945","repositories_listed":2,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/view-selection-for-3d-captioning-via","title":"View Selection for 3D Captioning via Diffusion Ranking","date":"2024-04-11","arxiv_id":"2404.07984","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"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":4,"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"}}