Timezone: »

Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D
Ankit Goyal · Kaiyu Yang · Dawei Yang · Jia Deng

Tue Dec 08 07:20 PM -- 07:30 PM (PST) @ Orals & Spotlights: Vision Applications

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.

Author Information

Ankit Goyal (Princeton University)
Kaiyu Yang (Princeton University)

I am a Ph.D. candidate in the Department of Computer Science at Princeton University, where I work with Prof. Jia Deng in Princeton Vision & Learning Lab. I also collaborate closely with Prof. Olga Russakovsky. My research focuses on bridging deep learning and symbolic reasoning, with applications in automated theorem proving and mathematical reasoning in natural languages. Prior to that, I worked in computer vision, including topics such as human poses, visual relationships, and fairness. I received my master’s degree from the University of Michigan and my bachelor’s degree from Tsinghua University.

Dawei Yang (University of Michigan)
Jia Deng (Princeton University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors