Presentation

· Contributors · Organizations · Search Program · My Schedule

Splat4D: Diffusion-Enhanced 4D Gaussian Splatting for Temporally and Spatially Consistent Content Creation

DescriptionSplat4D generates high-fidelity 4D content from monocular videos by integrating multi-view rendering, inconsistency identification, a video diffusion model, and asymmetric U-Net refinement. Our framework maintains spatial-temporal consistency while preserving details and following user guidance, achieving state-of-the-art benchmark performance. Applications include text/image-conditioned generation, 4D human modeling, and text-guided content editing.

Authors

Minghao Yin

University of Hong Kong

Yukang Cao

Nanyang Technological University, Singapore

Songyou Peng

Google DeepMind

Kai Han

University of Hong Kong