paper-with-me

홈 › Papers

MM-Gaussian: 3D Gaussian-based Multi-modal Fusion for Localization and Reconstruction in Unbounded Scenes

2024-04-05 · Chenyang Wu, Yifan Duan, Xinran Zhang, Yu Sheng, Jianmin Ji, Yanyong Zhang

Localization and mapping are critical tasks for various applications such as autonomous vehicles and robotics. The challenges posed by outdoor environments present particular complexities due to their unbounded characteristics. In this work, we present MM-Gaussian, a LiDAR-camera multi-modal fusion system for localization and mapping in unbounded scenes. Our approach is inspired by the recently developed 3D Gaussians, which demonstrate remarkable capabilities in achieving high rendering quality and fast rendering speed. Specifically, our system fully utilizes the geometric structure information provided by solid-state LiDAR to address the problem of inaccurate depth encountered when relying solely on visual solutions in unbounded, outdoor scenarios. Additionally, we utilize 3D Gaussian point clouds, with the assistance of pixel-level gradient descent, to fully exploit the color information in photos, thereby achieving realistic rendering effects. To further bolster the robustness of our system, we designed a relocalization module, which assists in returning to the correct trajectory in the event of a localization failure. Experiments conducted in multiple scenarios demonstrate the effectiveness of our method.

📄 PDF Abstract BibTeX arXiv:2404.04026

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Vehicles

Similar Papers 제목 키워드 기반

GaussianFusion: Unified 3D Gaussian Representation for Multi-Modal Fusion Perception

2026-07-01 · Xiao Zhao, Chang Liu, Mingxu Zhu, Zheyuan Zhang 외 arxiv

The bird's-eye view (BEV) representation enables multi-sensor features to be fused within a unified space, serving as the primary approach for achieving comprehensive 3D perception. However, the discrete grid representat…

3D Object Detection

RaGS: Unleashing 3D Gaussian Splatting from 4D Radar and Monocular Cues for 3D Object Detection

2025-07-26 · Xiaokai Bai, Chenxu Zhou, Lianqing Zheng, Si-Yuan Cao 외 arxiv

4D millimeter-wave radar is a promising sensing modality for autonomous driving, yet effective 3D object detection from 4D radar and monocular images remains challenging. Existing fusion approaches either rely on instanc…

3D Object DetectionAutonomous Driving

GaussFusion: Towards Multimodal 3D Gaussian Pretraining

2026-07-07 · Zhixuan You, Jihua Zhu, Yiding Sun, Zihao Guo 외 arxiv

3D Gaussian Splatting provides an explicit representation that jointly models geometry and appearance, serving as a scalable foundation for 3D representation learning. Existing pre-training methods for Gaussian represent…

Representation Learning

GaussianFusionOcc: A Seamless Sensor Fusion Approach for 3D Occupancy Prediction Using 3D Gaussians

2025-07-24 · Tomislav Pavković, Mohammad-Ali Nikouei Mahani, Johannes Niedermayer, Johannes Betz arxiv

3D semantic occupancy prediction is one of the crucial tasks of autonomous driving. It enables precise and safe interpretation and navigation in complex environments. Reliable predictions rely on effective sensor fusion,…

Autonomous Driving

GaussianFormer3D: Multi-Modal Gaussian-based Semantic Occupancy Prediction with 3D Deformable Attention

2025-05-15 · Lingjun Zhao, Sizhe Wei, James Hays, Lu Gan

3D semantic occupancy prediction is critical for achieving safe and reliable autonomous driving. Compared to camera-only perception systems, multi-modal pipelines, especially LiDAR-camera fusion methods, can produce more…

3D Semantic Occupancy PredictionAutonomous DrivingPrediction