# ProxyTransformation: Preshaping Point Cloud Manifold With Proxy Attention For 3D Visual Grounding

arXiv: https://arxiv.org/abs/2502.19247 · HTML: https://mlsanity.com/paper/2502.19247/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 75 references that are in the map.
- First posted on arXiv 26 Feb 2025.

## Builds on (most cited first, 30 of 47)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection](https://mlsanity.com/paper/1908.09492/) (2019)
- [PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation](https://mlsanity.com/paper/2004.01658/) (2020)
- [Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation](https://mlsanity.com/paper/1811.10092/) (2018)
- [Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2201.00520/) (2022)
- [PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers](https://mlsanity.com/paper/2108.08839/) (2021)
- [PU-Net: Point Cloud Upsampling Network](https://mlsanity.com/paper/1801.06761/) (2018)
- [RIO: 3D Object Instance Re-Localization in Changing Indoor Environments](https://mlsanity.com/paper/1908.06109/) (2019)
- [EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI](https://mlsanity.com/paper/2312.16170/) (2023)
- [Multi-View Transformer for 3D Visual Grounding](https://mlsanity.com/paper/2204.02174/) (2022)
- [Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds](https://mlsanity.com/paper/2112.08879/) (2021)
- [A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension](https://mlsanity.com/paper/1909.07072/) (2019)
- [Dynamic Graph Attention for Referring Expression Comprehension](https://mlsanity.com/paper/1909.08164/) (2019)
- [3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection](https://mlsanity.com/paper/2204.06272/) (2022)
- [PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds](https://mlsanity.com/paper/1901.01060/) (2019)
- [EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding](https://mlsanity.com/paper/2209.14941/) (2022)
- [POCO: Point Convolution for Surface Reconstruction](https://mlsanity.com/paper/2201.01831/) (2022)
- [Agent Attention: On the Integration of Softmax and Linear Attention](https://mlsanity.com/paper/2312.08874/) (2023)
- [LanguageRefer: Spatial-Language Model for 3D Visual Grounding](https://mlsanity.com/paper/2107.03438/) (2021)
- [Score-Based Point Cloud Denoising](https://mlsanity.com/paper/2107.10981/) (2021)
- [SCPNet: Semantic Scene Completion on Point Cloud](https://mlsanity.com/paper/2303.06884/) (2023)

## Built on by (most cited first, 5 of 5)

- [SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding](https://mlsanity.com/paper/2506.21924/) (2025)
- [ColaVLA: Leveraging Cognitive Latent Reasoning for Hierarchical Parallel Trajectory Planning in Autonomous Driving](https://mlsanity.com/paper/2512.22939/) (2025)
- [Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System](https://mlsanity.com/paper/2606.18112/) (2026)
- [DEGround: An Effective Baseline for Ego-centric 3D Visual Grounding with a Homogeneous Framework](https://mlsanity.com/paper/2506.05199/) (2025)
- [3D-DRES: Detailed 3D Referring Expression Segmentation](https://mlsanity.com/paper/2603.02896/) (2026)

## Abstract (arXiv)

Embodied intelligence requires agents to interact with 3D environments in real time based on language instructions. A foundational task in this domain is ego-centric 3D visual grounding. However, the point clouds rendered from RGB-D images retain a large amount of redundant background data and inherent noise, both of which can interfere with the manifold structure of the target regions. Existing point cloud enhancement methods often require a tedious process to improve the manifold, which is not suitable for real-time tasks. We propose Proxy Transformation suitable for multimodal task to efficiently improve the point cloud manifold. Our method first leverages Deformable Point Clustering to identify the point cloud sub-manifolds in target regions. Then, we propose a Proxy Attention module that utilizes multimodal proxies to guide point cloud transformation. Built upon Proxy Attention, we design a submanifold transformation generation module where textual information globally guides translation vectors for different submanifolds, optimizing relative spatial relationships of target regions. Simultaneously, image information guides linear transformations within each submanifold, refining the local point cloud manifold of target regions. Extensive experiments demonstrate that Proxy Transformation significantly outperforms all existing methods, achieving an impressive improvement of 7.49% on easy targets and 4.60% on hard targets, while reducing the computational overhead of attention blocks by 40.6%. These results establish a new SOTA in ego-centric 3D visual grounding, showcasing the effectiveness and robustness of our approach.