mlsanityData to 7 Oct 2026

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

arXiv 2012.01634 ↗First posted 3 Dec 2020cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 10; 2023: 4; 2024: 5; 2025: 6; 2026: 2.

30 papers.

Sort:

By area:

  1. 2023RVT: Robotic View Transformer for 3D Object Manipulationcited by 224
  2. 2021InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referringcited by 140
  3. 2025Scaling Spatial Intelligence with Multimodal Foundation Modelscited by 75
  4. 2025MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMscited by 72
  5. 2022X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioningcited by 70
  6. 2024Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Modelscited by 54
  7. 2022IFOR: Iterative Flow Minimization for Robotic Object Rearrangementcited by 42
  8. 20213D Question Answeringcited by 41
  9. 2023Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Groundingcited by 32
  10. 2022When are Lemons Purple? The Concept Association Bias of Vision-Language Modelscited by 23
  11. 2025Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluationcited by 23
  12. 20244D Panoptic Scene Graph Generationcited by 22
18 more
  1. 2022Mitigating Dataset Bias by Using Per-sample Gradientcited by 21
  2. 2025Can Multimodal Large Language Models Understand Spatial Relations?cited by 20
  3. 2022Affection: Learning Affective Explanations for Real-World Visual Datacited by 19
  4. 2024Can Transformers Capture Spatial Relations between Objects?cited by 11
  5. 2022What is Right for Me is Not Yet Right for You: A Dataset for Grounding Relative Directions via Multi-Task Learningcited by 10
  6. 20212.5D Visual Relationship Detectioncited by 7
  7. 2022Learning Point-Language Hierarchical Alignment for 3D Visual Groundingcited by 6
  8. 2024On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimationcited by 4
  9. 2023DetermiNet: A Large-Scale Diagnostic Dataset for Complex Visually-Grounded Referencing using Determinerscited by 3
  10. 2023STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoningcited by 3
  11. 20253D-Generalist: Self-Improving Vision-Language-Action Models for Crafting 3D Worldscited by 3
  12. 2024Structured Spatial Reasoning with Open Vocabulary Object Detectorscited by 2
  13. 2022Denoising after Entropy-based Debiasing A Robust Training Method for Dataset Bias with Noisy Labelscited by 1
  14. 2025Understanding Space Is Rocket Science -- Only Top Reasoning Models Can Solve Spatial Understanding Taskscited by 1
  15. 2026Enhancing MLLM Spatial Understanding via Active 3D Scene Exploration for Multi-Perspective Reasoningcited by 1
  16. 2022Knowing Earlier what Right Means to You: A Comprehensive VQA Dataset for Grounding Relative Directions via Multi-Task Learningcited by 0
  17. 2022Neuro-Symbolic Spatio-Temporal Reasoningcited by 0
  18. 2026SR-JEPA: Learning Predictive Latent State in 3D Scenescited by 0