Papers › SQA3D: Situated Question Answering in 3D Scenes

SQA3D: Situated Question Answering in 3D Scenes

14 Oct 2022arXiv:2210.07474archive 2025-07-28

Xiaojian Ma, Silong Yong, Zilong Zheng, Qing Li, Yitao Liang, Song-Chun Zhu, Siyuan Huang

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.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2210.07474")

Code

Syntology Ran 6 of 8 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 6 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

SilongYong/SQA3D officialmentioned on GitHubpytorch 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

8 samples harvested; 6 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

6ran
2unverified

Licence: 0 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from SilongYong/SQA3D. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

FC SilongYong/SQA3D/ScanQA/models/mcan_sqa_module.py official repository ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · d04a2cdda13f2c28 · report
FFN SilongYong/SQA3D/ScanQA/models/mcan_sqa_module.py official repository ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 5bdf1b882f558a79 · report
LayerNorm SilongYong/SQA3D/ScanQA/models/mcan_sqa_module.py official repository ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 82506e21f7dfa931 · report
MCAN_ED SilongYong/SQA3D/ScanQA/models/mcan_sqa_module.py official repository ran · metamorphic tier: deterministic Apache-2.0 (permissive) · b2942b89f2d00162 · report
MLP SilongYong/SQA3D/ScanQA/models/mcan_sqa_module.py official repository ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · a121cbb952a15dfc · report
SA SilongYong/SQA3D/ScanQA/models/mcan_sqa_module.py official repository ran · metamorphic tier: deterministic Apache-2.0 (permissive) · b17249e7a46ba6dc · report
MHAtt SilongYong/SQA3D/ScanQA/models/mcan_sqa_module.py official repository unverified Apache-2.0 (permissive) · 6a3f3f634cf6de1f · report
SGA SilongYong/SQA3D/ScanQA/models/mcan_sqa_module.py official repository unverified Apache-2.0 (permissive) · 02a7e6b69100fcd5 · report

Tasks

Question AnsweringReferring ExpressionScene Understanding

Datasets

Introduced by this paper, per the archive.

SQA3D

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering SQA3D ScanQA (w/ auxiliary loss) AnswerExactMatch (Question Answering) 47.20 #5 of 7 Archive leaderboard report
Question Answering SQA3D ScanQA AnswerExactMatch (Question Answering) 46.58 #6 of 7 Archive leaderboard report
Referring Expression SQA3D Random Acc@0.5m 14.60 #1 of 1 Archive leaderboard report
Referring Expression SQA3D Random Acc@1.0m 34.21 #1 of 1 Archive leaderboard report
Referring Expression SQA3D Random Acc@15° 22.39 #1 of 1 Archive leaderboard report
Referring Expression SQA3D Random Acc@30° 42.28 #1 of 1 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