代码库
[CVPR 2025] GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding
Python
[NeurIPS 2025] RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning
Python
[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
Jupyter Notebook
3dcomputer-visioncvpr2024dynamic-scenegaussian-splattinggraphicsneural-networkneural-renderingnovel-view-synthesisradiance-field
Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"
Python
multimodalmultimodal-large-language-modelsreferring-image-segmentationsegment-anythingsegmentation
PixelHacker: Image Inpainting with Structural and Semantic Consistency
Python