3D Gaussian
3D Gaussian splatting is an explicit 3D scene representation technique that uses collections of 3D Gaussian functions to model objects and scenes, aiming for high-quality, real-time rendering. Current research focuses on improving the accuracy and efficiency of 3D Gaussian splatting, particularly addressing challenges like view-dependent effects, sparse viewpoints, and the handling of dynamic objects and large-scale scenes through various optimization strategies and model architectures. This approach offers significant advantages in applications such as novel view synthesis, 3D object detection, augmented reality, and even multimodal place recognition by providing a compact yet detailed representation of 3D environments.
Papers
InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior
Zhiheng Liu, Hao Ouyang, Qiuyu Wang, Ka Leong Cheng, Jie Xiao, Kai Zhu, Nan Xue, Yu Liu, Yujun Shen, Yang Cao
DeblurGS: Gaussian Splatting for Camera Motion Blur
Jeongtaek Oh, Jaeyoung Chung, Dongwoo Lee, Kyoung Mu Lee
SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer
Zijie Wu, Chaohui Yu, Yanqin Jiang, Chenjie Cao, Fan Wang, Xiang Bai
DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling
Haoran Li, Haolin Shi, Wenli Zhang, Wenjun Wu, Yong Liao, Lin Wang, Lik-hang Lee, Pengyuan Zhou