3D Gaussian Splat
3D Gaussian splatting is a novel 3D scene representation technique that uses collections of 3D Gaussian functions to model surfaces and volumes, offering efficient rendering and high-quality reconstruction. Current research focuses on improving the accuracy and efficiency of these representations, exploring variations like space-time splats for dynamic scenes, language-embedded splats for semantic mapping, and compressed representations for reduced storage and faster rendering. This approach holds significant promise for applications in robotics, augmented reality, and volumetric video streaming due to its speed, scalability, and ability to represent both geometric and semantic information.
Papers
Unleashing the Power of Data Synthesis in Visual Localization
Sihang Li, Siqi Tan, Bowen Chang, Jing Zhang, Chen Feng, Yiming Li
SuperGaussians: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors
Rui Xu, Wenyue Chen, Jiepeng Wang, Yuan Liu, Peng Wang, Lin Gao, Shiqing Xin, Taku Komura, Xin Li, Wenping Wang