4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
Huazhong University of Science and Technology
Abstract
Representing and rendering dynamic scenes has been an important but challenging task. Especially, to accurately model complex motions, high efficiency is usually hard to guarantee. To achieve real-time dynamic scene rendering while also enjoying high training and storage efficiency, we propose 4D Gaussian Splatting (4D-GS) as a holistic representation for dynamic scenes rather than applying 3D-GS for each individual frame. In 4D-GS, a novel explicit representation containing both 3D Gaussians and 4D neural voxels is proposed. A decomposed neural voxel encoding algorithm inspired by HexPlane is proposed to efficiently build Gaussian features from 4D neural voxels and then a lightweight MLP is applied to predict…
Citation impact
- FWCI
- 291.26
- Percentile
- 100%
- References
- 67
Authors
9Topics & keywords
- Computer science
- Computer graphics (images)
- Rendering (computer graphics)
- Real-time rendering
- Gaussian
- Computer vision
- Artificial intelligence