Papers › Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D

Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D

3 Dec 2020NeurIPS 2020 12arXiv:2012.01634archive 2025-07-28

Ankit Goyal, Kaiyu Yang, Dawei Yang, Jia Deng

Understanding spatial relations (e.g., "laptop on table") in visual input is important for both humans and robots. Existing datasets are insufficient as they lack large-scale, high-quality 3D ground truth information, which is critical for learning spatial relations. In this paper, we fill this gap by constructing Rel3D: the first large-scale, human-annotated dataset for grounding spatial relations in 3D. Rel3D enables quantifying the effectiveness of 3D information in predicting spatial relations on large-scale human data. Moreover, we propose minimally contrastive data collection -- a novel crowdsourcing method for reducing dataset bias. The 3D scenes in our dataset come in minimally contrastive pairs: two scenes in a pair are almost identical, but a spatial relation holds in one and fails in the other. We empirically validate that minimally contrastive examples can diagnose issues with current relation detection models as well as lead to sample-efficient training. Code and data are available at https://github.com/princeton-vl/Rel3D.

PaperPDFConference PDFCode

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

Code

princeton-vl/Rel3D officialmentioned in papermentioned on GitHubpytorch report
princeton-vl/SpatialSense mentioned 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

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

Tasks

Spatial Relation Recognition

1 archive task tag without a task page not shown.

Datasets

Introduced by this paper, per the archive.

Rel3D

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Spatial Relation Recognition Rel3D Human Acc 94.25 #1 of 9 Archive leaderboard report
Spatial Relation Recognition Rel3D MLP-Aligned Features Acc 85.03 #2 of 9 Archive leaderboard report
Spatial Relation Recognition Rel3D MLP-Raw Features Acc 81.24 #3 of 9 Archive leaderboard report
Spatial Relation Recognition Rel3D BBox Only Acc 74.14 #4 of 9 Archive leaderboard report
Spatial Relation Recognition Rel3D PPR-FCN Acc 73.3 #5 of 9 Archive leaderboard report
Spatial Relation Recognition Rel3D DRNet Acc 73.25 #6 of 9 Archive leaderboard report
Spatial Relation Recognition Rel3D VipCNN Acc 72.32 #7 of 9 Archive leaderboard report
Spatial Relation Recognition Rel3D VTransE Acc 72.27 #8 of 9 Archive leaderboard report
Spatial Relation Recognition Rel3D Random Acc 50 #9 of 9 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