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

arXiv: https://arxiv.org/abs/2012.01634 · HTML: https://mlsanity.com/paper/2012.01634/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 30 of 30)

- [RVT: Robotic View Transformer for 3D Object Manipulation](https://mlsanity.com/paper/2306.14896/) (2023)
- [InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring](https://mlsanity.com/paper/2103.01128/) (2021)
- [Scaling Spatial Intelligence with Multimodal Foundation Models](https://mlsanity.com/paper/2511.13719/) (2025)
- [MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs](https://mlsanity.com/paper/2503.13111/) (2025)
- [X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning](https://mlsanity.com/paper/2203.00843/) (2022)
- [Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models](https://mlsanity.com/paper/2409.09788/) (2024)
- [IFOR: Iterative Flow Minimization for Robotic Object Rearrangement](https://mlsanity.com/paper/2202.00732/) (2022)
- [3D Question Answering](https://mlsanity.com/paper/2112.08359/) (2021)
- [Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding](https://mlsanity.com/paper/2309.04561/) (2023)
- [Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation](https://mlsanity.com/paper/2506.21876/) (2025)
- [When are Lemons Purple? The Concept Association Bias of Vision-Language Models](https://mlsanity.com/paper/2212.12043/) (2022)
- [Mitigating Dataset Bias by Using Per-sample Gradient](https://mlsanity.com/paper/2205.15704/) (2022)
- [4D Panoptic Scene Graph Generation](https://mlsanity.com/paper/2405.10305/) (2024)
- [Can Multimodal Large Language Models Understand Spatial Relations?](https://mlsanity.com/paper/2505.19015/) (2025)
- [Affection: Learning Affective Explanations for Real-World Visual Data](https://mlsanity.com/paper/2210.01946/) (2022)
- [Can Transformers Capture Spatial Relations between Objects?](https://mlsanity.com/paper/2403.00729/) (2024)
- [What is Right for Me is Not Yet Right for You: A Dataset for Grounding Relative Directions via Multi-Task Learning](https://mlsanity.com/paper/2205.02671/) (2022)
- [2.5D Visual Relationship Detection](https://mlsanity.com/paper/2104.12727/) (2021)
- [Learning Point-Language Hierarchical Alignment for 3D Visual Grounding](https://mlsanity.com/paper/2210.12513/) (2022)
- [On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation](https://mlsanity.com/paper/2404.08540/) (2024)
- [DetermiNet: A Large-Scale Diagnostic Dataset for Complex Visually-Grounded Referencing using Determiners](https://mlsanity.com/paper/2309.03483/) (2023)
- [STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoning](https://mlsanity.com/paper/2309.06680/) (2023)
- [3D-Generalist: Self-Improving Vision-Language-Action Models for Crafting 3D Worlds](https://mlsanity.com/paper/2507.06484/) (2025)
- [Structured Spatial Reasoning with Open Vocabulary Object Detectors](https://mlsanity.com/paper/2410.07394/) (2024)
- [Denoising after Entropy-based Debiasing A Robust Training Method for Dataset Bias with Noisy Labels](https://mlsanity.com/paper/2212.01189/) (2022)
- [Understanding Space Is Rocket Science -- Only Top Reasoning Models Can Solve Spatial Understanding Tasks](https://mlsanity.com/paper/2509.02175/) (2025)
- [Enhancing MLLM Spatial Understanding via Active 3D Scene Exploration for Multi-Perspective Reasoning](https://mlsanity.com/paper/2604.06725/) (2026)
- [Knowing Earlier what Right Means to You: A Comprehensive VQA Dataset for Grounding Relative Directions via Multi-Task Learning](https://mlsanity.com/paper/2207.02624/) (2022)
- [Neuro-Symbolic Spatio-Temporal Reasoning](https://mlsanity.com/paper/2211.15566/) (2022)
- [SR-JEPA: Learning Predictive Latent State in 3D Scenes](https://mlsanity.com/paper/2608.05774/) (2026)

## 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.