On June 25, 2025, Lunar Lab member Lingjun Zhao presented his research on GaussianFormer3D: Multi-Modal Gaussian-based Semantic Occupancy Prediction with 3D Deformable Attention in the workshop on Gaussian Representations for Robot Autonomy: Challenges and Opportunities at Robotics: Science and Systems (RSS) 2025. The work explores Gaussian-based scene representations of multi-modal data for semantic occupancy prediction, advancing efficient robot perception and autonomy.
Related Publication
- L. Zhao, S. Wei, J. Hays and L. Gan, “GaussianFormer3D: Multi-Modal Gaussian-based Semantic Occupancy Prediction with 3D Deformable Attention“, RSS 2025 Gaussian Representations for Robot Autonomy Workshop, 2025.
