STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians

arXiv:2403.14939v1 Announce Type: new
Abstract: Recent progress in pre-trained diffusion models and 3D generation have spurred interest in 4D content creation. However, achieving high-fidelity 4D generation with spatial-temporal consistency remains a challenge. In this work, we propose STAG4D, a novel framework that combines pre-trained diffusion models with dynamic 3D Gaussian splatting for high-fidelity 4D generation. Drawing inspiration from 3D generation techniques, we utilize a multi-view diffusion model to initialize multi-view images anchoring on the input video frames, where the video …

abstract arxiv challenge cs.cv diffusion diffusion models dynamic fidelity framework generative however novel progress spatial temporal type work