{"url":"/task/3d-dense-captioning","name":"3D dense captioning","slug":"3d-dense-captioning","description_markdown":"Dense captioning in 3D point clouds is an emerging vision-and-language task involving object-level 3D scene understanding. Apart from coarse semantic class prediction and bounding box regression as in traditional 3D object detection, 3D dense captioning aims at producing a further and finer instance-level label of natural language description on visual appearance and spatial relations for each scene object of interest.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":26,"papers_with_code":13,"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/3d-dense-captioning-on-scanrefer-dataset","slug":"3d-dense-captioning-on-scanrefer-dataset","dataset":"ScanRefer Dataset","dataset_url":"/dataset/scanrefer-dataset","rows_in_archive":12,"metrics":["CIDEr","BLEU-4","METEOR","ROUGE-L"],"first_row_in_archive_order":{"model":"3D CoCa","paper_title":"3D CoCa: Contrastive Learners are 3D Captioners","paper_url":"/paper/3d-coca-contrastive-learners-are-3d","paper_date":"2025-04-13","arxiv_id":"2504.09518","code_links":[{"title":"AIGeeksGroup/3DCoCa","url":"https://github.com/AIGeeksGroup/3DCoCa"}],"syntology":null}},{"leaderboard":"/sota/3d-dense-captioning-on-nr3d","slug":"3d-dense-captioning-on-nr3d","dataset":"Nr3D","dataset_url":"/dataset/referit3d","rows_in_archive":10,"metrics":["CIDEr","BLEU-4","METEOR","ROUGE-L"],"first_row_in_archive_order":{"model":"3D CoCa","paper_title":"3D CoCa: Contrastive Learners are 3D Captioners","paper_url":"/paper/3d-coca-contrastive-learners-are-3d","paper_date":"2025-04-13","arxiv_id":"2504.09518","code_links":[{"title":"AIGeeksGroup/3DCoCa","url":"https://github.com/AIGeeksGroup/3DCoCa"}],"syntology":null}}],"datasets":[{"url":"/dataset/referit3d","name":"ReferIt3D","full_name":"","num_papers_in_archive":104},{"url":"/dataset/scanrefer-dataset","name":"ScanRefer Dataset","full_name":"","num_papers_in_archive":63}],"subtasks":[],"parent_tasks":[{"url":"/task/image-captioning","name":"Image Captioning"}],"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":13,"of":13,"tagged_in_all":26,"items":[{"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/3d-coca-contrastive-learners-are-3d","title":"3D CoCa: Contrastive Learners are 3D Captioners","date":"2025-04-13","arxiv_id":"2504.09518","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-3d-dense-caption-and-visual","title":"Rethinking 3D Dense Caption and Visual Grounding in A Unified Framework through Prompt-based Localization","date":"2024-04-17","arxiv_id":"2404.11064","repositories_listed":1,"syntology":null},{"url":"/paper/tod3cap-towards-3d-dense-captioning-in","title":"TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes","date":"2024-03-28","arxiv_id":"2403.19589","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_unverified":6,"n_pointer_only":16}},{"url":"/paper/ll3da-visual-interactive-instruction-tuning-1","title":"LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding Reasoning and Planning","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ll3da-visual-interactive-instruction-tuning","title":"LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning","date":"2023-11-30","arxiv_id":"2311.18651","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/an-embodied-generalist-agent-in-3d-world","title":"An Embodied Generalist Agent in 3D World","date":"2023-11-18","arxiv_id":"2311.12871","repositories_listed":1,"syntology":{"n":13,"n_ran":3,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/vote2cap-detr-decoupling-localization-and","title":"Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning","date":"2023-09-06","arxiv_id":"2309.02999","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-3d-dense-captioning-with-vote2cap","title":"End-to-End 3D Dense Captioning with Vote2Cap-DETR","date":"2023-01-06","arxiv_id":"2301.02508","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/context-aware-alignment-and-mutual-masking","title":"Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/spatiality-guided-transformer-for-3d-dense","title":"Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds","date":"2022-04-22","arxiv_id":"2204.10688","repositories_listed":1,"syntology":null},{"url":"/paper/more-multi-order-relation-mining-for-dense","title":"MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes","date":"2022-03-10","arxiv_id":"2203.05203","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/x-trans2cap-cross-modal-knowledge-transfer","title":"X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning","date":"2022-03-02","arxiv_id":"2203.00843","repositories_listed":1,"syntology":null}],"syntology_records":6,"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":"2026-09-25T09:33:49+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"}}