This is the public, feature-limited version of the conference webpage. After Registration and login please visit the full version.

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

Ankit Goyal, Kaiyu Yang, Dawei Yang, Jia Deng

Spotlight presentation: Orals & Spotlights Track 12: Vision Applications
on 2020-12-08T19:20:00-08:00 - 2020-12-08T19:30:00-08:00
Poster Session 3 (more posters)
on 2020-12-08T21:00:00-08:00 - 2020-12-08T23:00:00-08:00
Abstract: 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.

Preview Video and Chat

To see video, interact with the author and ask questions please use registration and login.