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
MVG-Splatting: Multi-View Guided Gaussian Splatting with Adaptive Quantile-Based Geometric Consistency Densification
Zhuoxiao Li, Shanliang Yao, Yijie Chu, Angel F. Garcia-Fernandez, Yong Yue, Eng Gee Lim, Xiaohui Zhu
Click-Gaussian: Interactive Segmentation to Any 3D Gaussians
Seokhun Choi, Hyeonseop Song, Jaechul Kim, Taehyeong Kim, Hoseok Do