Papers › ScanQA: 3D Question Answering for Spatial Scene Understanding

ScanQA: 3D Question Answering for Spatial Scene Understanding

20 Dec 2021CVPR 2022 1arXiv:2112.10482archive 2025-07-28

Daichi Azuma, Taiki Miyanishi, Shuhei Kurita, Motoaki Kawanabe

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.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

atr-dbi/scanqa officialmentioned in papermentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Question Answering (3D-QA)ObjectObject LocalizationQuestion AnsweringScene UnderstandingSentenceSentence EmbeddingsVisual Question Answering (VQA)

Datasets

Introduced by this paper, per the archive.

ScanQA

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Question Answering (3D-QA) SQA3D ScanQA Exact Match 47.2 #9 of 13 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects ScanQA BLEU-1 31.56 #7 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects ScanQA BLEU-4 12.04 #7 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects ScanQA CIDEr 67.29 #7 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects ScanQA Exact Match 23.45 #7 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects ScanQA METEOR 13.55 #7 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects ScanQA ROUGE 34.34 #7 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects ScanRefer+MCAN BLEU-1 27.85 #11 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects ScanRefer+MCAN BLEU-4 7.46 #11 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects ScanRefer+MCAN CIDEr 57.56 #11 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects ScanRefer+MCAN Exact Match 20.56 #11 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects ScanRefer+MCAN METEOR 11.97 #11 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects ScanRefer+MCAN ROUGE 30.68 #11 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects VoteNet+MCAN BLEU-1 29.46 #12 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects VoteNet+MCAN BLEU-4 6.08 #12 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects VoteNet+MCAN CIDEr 58.23 #12 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects VoteNet+MCAN Exact Match 19.71 #12 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects VoteNet+MCAN METEOR 12.07 #12 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects VoteNet+MCAN ROUGE 30.97 #12 of 18 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections