# Talk2PC: Enhancing 3D Visual Grounding through LiDAR and Radar Point Clouds Fusion for Autonomous Driving

arXiv: https://arxiv.org/abs/2503.08336 · HTML: https://mlsanity.com/paper/2503.08336/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLMs for autonomous driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 28 of its 44 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Placed in

- End-to-end autonomous driving / [VLMs for autonomous driving](https://mlsanity.com/driving/vlms-for-autonomous-driving/)

## Builds on (most cited first, 28 of 28)

- [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)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [Talk2Car: Taking Control of Your Self-Driving Car](https://mlsanity.com/paper/1909.10838/) (2019)
- [SeqTR: A Simple yet Universal Network for Visual Grounding](https://mlsanity.com/paper/2203.16265/) (2022)
- [3D Object Detection for Autonomous Driving: A Survey](https://mlsanity.com/paper/2106.10823/) (2021)
- [CenterFormer: Center-based Transformer for 3D Object Detection](https://mlsanity.com/paper/2209.05588/) (2022)
- [EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding](https://mlsanity.com/paper/2209.14941/) (2022)
- [Referring Multi-Object Tracking](https://mlsanity.com/paper/2303.03366/) (2023)
- [MobileViG: Graph-Based Sparse Attention for Mobile Vision Applications](https://mlsanity.com/paper/2307.00395/) (2023)
- [L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection](https://mlsanity.com/paper/2408.03677/) (2024)
- [Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection](https://mlsanity.com/paper/2306.01438/) (2023)
- [RaLiBEV: Radar and LiDAR BEV Fusion Learning for Anchor Box Free Object Detection Systems](https://mlsanity.com/paper/2211.06108/) (2022)
- [Mono3DVG: 3D Visual Grounding in Monocular Images](https://mlsanity.com/paper/2312.08022/) (2023)
- [Language-Guided 3D Object Detection in Point Cloud for Autonomous Driving](https://mlsanity.com/paper/2305.15765/) (2023)
- [Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression Comprehension](https://mlsanity.com/paper/2405.12821/) (2024)
- [MSSF: A 4D Radar and Camera Fusion Framework With Multi-Stage Sampling for 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/2411.15016/) (2024)
- [WaterVG: Waterway Visual Grounding based on Text-Guided Vision and mmWave Radar](https://mlsanity.com/paper/2403.12686/) (2024)
- [LiRaFusion: Deep Adaptive LiDAR-Radar Fusion for 3D Object Detection](https://mlsanity.com/paper/2402.11735/) (2024)
- [Leveraging Anchor-based LiDAR 3D Object Detection via Point Assisted Sample Selection](https://mlsanity.com/paper/2403.01978/) (2024)

## Abstract (arXiv)

Embodied outdoor scene understanding forms the foundation for autonomous agents to perceive, analyze, and react to dynamic driving environments. However, existing 3D understanding is predominantly based on 2D Vision-Language Models (VLMs), which collect and process limited scene-aware contexts. In contrast, compared to the 2D planar visual information, point cloud sensors such as LiDAR provide rich depth and fine-grained 3D representations of objects. Even better the emerging 4D millimeter-wave radar detects the motion trend, velocity, and reflection intensity of each object. The integration of these two modalities provides more flexible querying conditions for natural language, thereby supporting more accurate 3D visual grounding. To this end, we propose a novel method called TPCNet, the first outdoor 3D visual grounding model upon the paradigm of prompt-guided point cloud sensor combination, including both LiDAR and radar sensors. To optimally combine the features of these two sensors required by the prompt, we design a multi-fusion paradigm called Two-Stage Heterogeneous Modal Adaptive Fusion. Specifically, this paradigm initially employs Bidirectional Agent Cross-Attention (BACA), which feeds both-sensor features, characterized by global receptive fields, to the text features for querying. Moreover, we design a Dynamic Gated Graph Fusion (DGGF) module to locate the regions of interest identified by the queries. To further enhance accuracy, we devise an C3D-RECHead, based on the nearest object edge to the ego-vehicle. Experimental results demonstrate that our TPCNet, along with its individual modules, achieves the state-of-the-art performance on both the Talk2Radar and Talk2Car datasets. We release the code at https://github.com/GuanRunwei/TPCNet.