{"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/sqa3d-situated-question-answering-in-3d","title":"SQA3D: Situated Question Answering in 3D Scenes","arxiv_id":"2210.07474","date":"2022-10-14","proceeding":null,"authors":["Xiaojian Ma","Silong Yong","Zilong Zheng","Qing Li","Yitao Liang","Song-Chun Zhu","Siyuan Huang"],"abstract":"We propose a new task to benchmark scene understanding of embodied agents: Situated Question Answering in 3D Scenes (SQA3D). Given a scene context (e.g., 3D scan), SQA3D requires the tested agent to first understand its situation (position, orientation, etc.) in the 3D scene as described by text, then reason about its surrounding environment and answer a question under that situation. Based upon 650 scenes from ScanNet, we provide a dataset centered around 6.8k unique situations, along with 20.4k descriptions and 33.4k diverse reasoning questions for these situations. These questions examine a wide spectrum of reasoning capabilities for an intelligent agent, ranging from spatial relation comprehension to commonsense understanding, navigation, and multi-hop reasoning. SQA3D imposes a significant challenge to current multi-modal especially 3D reasoning models. We evaluate various state-of-the-art approaches and find that the best one only achieves an overall score of 47.20%, while amateur human participants can reach 90.06%. We believe SQA3D could facilitate future embodied AI research with stronger situation understanding and reasoning capability.","url_abs":"https://arxiv.org/abs/2210.07474v5","url_pdf":"https://arxiv.org/pdf/2210.07474v5.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":"sqa3d-situated-question-answering-in-3d","repo_url":"https://github.com/SilongYong/SQA3D","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"referring-expression","task_name":"Referring Expression"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"}],"methods":[],"datasets_introduced":[{"slug":"sqa3d","name":"SQA3D","full_name":"Situated Question Answering in 3D Scenes"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-sqa3d","task":"Question Answering","dataset":"SQA3D","model":"ScanQA (w/ auxiliary loss)","rank_in_archive_order":5,"of":7,"metrics":{"AnswerExactMatch (Question Answering)":"47.20"},"uses_additional_data":true},{"leaderboard":"/sota/question-answering-on-sqa3d","task":"Question Answering","dataset":"SQA3D","model":"ScanQA","rank_in_archive_order":6,"of":7,"metrics":{"AnswerExactMatch (Question Answering)":"46.58"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-on-sqa3d-1","task":"Referring Expression","dataset":"SQA3D","model":"Random","rank_in_archive_order":1,"of":1,"metrics":{"Acc@0.5m":"14.60","Acc@1.0m":"34.21","Acc@15°":"22.39","Acc@30°":"42.28"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.07474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07474"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SilongYong/SQA3D","reach":null}],"summary":{"ran":6,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"d04a2cdda13f2c28","entry":"FC","repo":"SilongYong/SQA3D","repo_kind":"official","path":"ScanQA/models/mcan_sqa_module.py","file_url":"https://github.com/SilongYong/SQA3D/blob/HEAD/ScanQA/models/mcan_sqa_module.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d04a2cdda13f2c28"}},{"code_sha256_prefix":"5bdf1b882f558a79","entry":"FFN","repo":"SilongYong/SQA3D","repo_kind":"official","path":"ScanQA/models/mcan_sqa_module.py","file_url":"https://github.com/SilongYong/SQA3D/blob/HEAD/ScanQA/models/mcan_sqa_module.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5bdf1b882f558a79"}},{"code_sha256_prefix":"82506e21f7dfa931","entry":"LayerNorm","repo":"SilongYong/SQA3D","repo_kind":"official","path":"ScanQA/models/mcan_sqa_module.py","file_url":"https://github.com/SilongYong/SQA3D/blob/HEAD/ScanQA/models/mcan_sqa_module.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"82506e21f7dfa931"}},{"code_sha256_prefix":"b2942b89f2d00162","entry":"MCAN_ED","repo":"SilongYong/SQA3D","repo_kind":"official","path":"ScanQA/models/mcan_sqa_module.py","file_url":"https://github.com/SilongYong/SQA3D/blob/HEAD/ScanQA/models/mcan_sqa_module.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b2942b89f2d00162"}},{"code_sha256_prefix":"a121cbb952a15dfc","entry":"MLP","repo":"SilongYong/SQA3D","repo_kind":"official","path":"ScanQA/models/mcan_sqa_module.py","file_url":"https://github.com/SilongYong/SQA3D/blob/HEAD/ScanQA/models/mcan_sqa_module.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a121cbb952a15dfc"}},{"code_sha256_prefix":"b17249e7a46ba6dc","entry":"SA","repo":"SilongYong/SQA3D","repo_kind":"official","path":"ScanQA/models/mcan_sqa_module.py","file_url":"https://github.com/SilongYong/SQA3D/blob/HEAD/ScanQA/models/mcan_sqa_module.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b17249e7a46ba6dc"}},{"code_sha256_prefix":"6a3f3f634cf6de1f","entry":"MHAtt","repo":"SilongYong/SQA3D","repo_kind":"official","path":"ScanQA/models/mcan_sqa_module.py","file_url":"https://github.com/SilongYong/SQA3D/blob/HEAD/ScanQA/models/mcan_sqa_module.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6a3f3f634cf6de1f"}},{"code_sha256_prefix":"02a7e6b69100fcd5","entry":"SGA","repo":"SilongYong/SQA3D","repo_kind":"official","path":"ScanQA/models/mcan_sqa_module.py","file_url":"https://github.com/SilongYong/SQA3D/blob/HEAD/ScanQA/models/mcan_sqa_module.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"02a7e6b69100fcd5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}