# RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation

arXiv: https://arxiv.org/abs/2412.02402 · HTML: https://mlsanity.com/paper/2412.02402/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 78 references that are in the map.
- First posted on arXiv 3 Dec 2024.

## Builds on (most cited first, 30 of 64)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)
- [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021)
- [Rethinking and Improving Relative Position Encoding for Vision Transformer](https://mlsanity.com/paper/2107.14222/) (2021)
- [3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment](https://mlsanity.com/paper/2308.04352/) (2023)
- [Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning](https://mlsanity.com/paper/2403.11401/) (2024)
- [Stratified Transformer for 3D Point Cloud Segmentation](https://mlsanity.com/paper/2203.14508/) (2022)
- [Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition](https://mlsanity.com/paper/2501.03230/) (2024)
- [InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring](https://mlsanity.com/paper/2103.01128/) (2021)
- [Towards Learning a Generalist Model for Embodied Navigation](https://mlsanity.com/paper/2312.02010/) (2023)
- [Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes](https://mlsanity.com/paper/2308.08769/) (2023)
- [Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds](https://mlsanity.com/paper/2112.08879/) (2021)
- [SAT: 2D Semantics Assisted Training for 3D Visual Grounding](https://mlsanity.com/paper/2105.11450/) (2021)
- [Language Conditioned Spatial Relation Reasoning for 3D Object Grounding](https://mlsanity.com/paper/2211.09646/) (2022)
- [ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension](https://mlsanity.com/paper/2204.05991/) (2022)

## Built on by (most cited first, 11 of 11)

- [Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes](https://mlsanity.com/paper/2509.06266/) (2025)
- [Multimodal Referring Segmentation: A Survey](https://mlsanity.com/paper/2508.00265/) (2025)
- [Language-to-Space Programming for Training-Free 3D Visual Grounding](https://mlsanity.com/paper/2502.01401/) (2025)
- [MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation](https://mlsanity.com/paper/2601.06874/) (2026)
- [DEGround: An Effective Baseline for Ego-centric 3D Visual Grounding with a Homogeneous Framework](https://mlsanity.com/paper/2506.05199/) (2025)
- [ZeroSplat: Generalized Referring Segmentation in 3D Gaussian Splatting](https://mlsanity.com/paper/2607.18801/) (2026)
- [3DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentation](https://mlsanity.com/paper/2504.12599/) (2025)
- [What is the Right Embedding Space for Contrastive Learning in Referring Expression Counting?](https://mlsanity.com/paper/2505.22850/) (2025)
- [HiFi-Mesh: High-Fidelity Efficient 3D Mesh Generation via Compact Autoregressive Dependence](https://mlsanity.com/paper/2601.21314/) (2026)
- [TrackRef3D: Multi-View Consistent Track-then-Label for Open-World Referring Segmentation in 3D Gaussian Splatting](https://mlsanity.com/paper/2605.26576/) (2026)
- [Hierarchical Collaborative Fusion for 3D Instance-aware Referring Expression Segmentation](https://mlsanity.com/paper/2603.06250/) (2026)

## Abstract (arXiv)

3D Referring Expression Segmentation (3D-RES) aims to segment 3D objects by correlating referring expressions with point clouds. However, traditional approaches frequently encounter issues like over-segmentation or mis-segmentation, due to insufficient emphasis on spatial information of instances. In this paper, we introduce a Rule-Guided Spatial Awareness Network (RG-SAN) by utilizing solely the spatial information of the target instance for supervision. This approach enables the network to accurately depict the spatial relationships among all entities described in the text, thus enhancing the reasoning capabilities. The RG-SAN consists of the Text-driven Localization Module (TLM) and the Rule-guided Weak Supervision (RWS) strategy. The TLM initially locates all mentioned instances and iteratively refines their positional information. The RWS strategy, acknowledging that only target objects have supervised positional information, employs dependency tree rules to precisely guide the core instance's positioning. Extensive testing on the ScanRefer benchmark has shown that RG-SAN not only establishes new performance benchmarks, with an mIoU increase of 5.1 points, but also exhibits significant improvements in robustness when processing descriptions with spatial ambiguity. All codes are available at https://github.com/sosppxo/RG-SAN.