{"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/scanqa-3d-question-answering-for-spatial","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","arxiv_id":"2112.10482","date":"2021-12-20","proceeding":"CVPR 2022 1","authors":["Daichi Azuma","Taiki Miyanishi","Shuhei Kurita","Motoaki Kawanabe"],"abstract":"We propose a new 3D spatial understanding task of 3D Question Answering (3D-QA). In the 3D-QA task, models receive visual information from the entire 3D scene of the rich RGB-D indoor scan and answer the given textual questions about the 3D scene. Unlike the 2D-question answering of VQA, the conventional 2D-QA models suffer from problems with spatial understanding of object alignment and directions and fail the object identification from the textual questions in 3D-QA. We propose a baseline model for 3D-QA, named ScanQA model, where the model learns a fused descriptor from 3D object proposals and encoded sentence embeddings. This learned descriptor correlates the language expressions with the underlying geometric features of the 3D scan and facilitates the regression of 3D bounding boxes to determine described objects in textual questions and outputs correct answers. We collected human-edited question-answer pairs with free-form answers that are grounded to 3D objects in each 3D scene. Our new ScanQA dataset contains over 40K question-answer pairs from the 800 indoor scenes drawn from the ScanNet dataset. To the best of our knowledge, the proposed 3D-QA task is the first large-scale effort to perform object-grounded question-answering in 3D environments.","url_abs":"https://arxiv.org/abs/2112.10482v3","url_pdf":"https://arxiv.org/pdf/2112.10482v3.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":"scanqa-3d-question-answering-for-spatial","repo_url":"https://github.com/atr-dbi/scanqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"3d-question-answering-3d-qa","task_name":"3D Question Answering (3D-QA)"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embeddings","task_name":"Sentence Embeddings"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[{"slug":"scanqa","name":"ScanQA","full_name":"ScanQA: 3D Question Answering for Spatial Scene Understanding"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-question-answering-3d-qa-on-sqa3d","task":"3D Question Answering (3D-QA)","dataset":"SQA3D","model":"ScanQA","rank_in_archive_order":9,"of":13,"metrics":{"Exact Match":"47.2"},"uses_additional_data":false},{"leaderboard":"/sota/3d-question-answering-3d-qa-on-scanqa-test-w","task":"3D Question Answering (3D-QA)","dataset":"ScanQA Test w/ objects","model":"ScanQA","rank_in_archive_order":7,"of":18,"metrics":{"BLEU-1":"31.56","BLEU-4":"12.04","CIDEr":"67.29","Exact Match":"23.45","METEOR":"13.55","ROUGE":"34.34"},"uses_additional_data":false},{"leaderboard":"/sota/3d-question-answering-3d-qa-on-scanqa-test-w","task":"3D Question Answering (3D-QA)","dataset":"ScanQA Test w/ objects","model":"ScanRefer+MCAN","rank_in_archive_order":11,"of":18,"metrics":{"BLEU-1":"27.85","BLEU-4":"7.46","CIDEr":"57.56","Exact Match":"20.56","METEOR":"11.97","ROUGE":"30.68"},"uses_additional_data":false},{"leaderboard":"/sota/3d-question-answering-3d-qa-on-scanqa-test-w","task":"3D Question Answering (3D-QA)","dataset":"ScanQA Test w/ objects","model":"VoteNet+MCAN","rank_in_archive_order":12,"of":18,"metrics":{"BLEU-1":"29.46","BLEU-4":"6.08","CIDEr":"58.23","Exact Match":"19.71","METEOR":"12.07","ROUGE":"30.97"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.10482","atlas_url":"https://app.syntology.ai/?focus=2112.10482","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}