SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency

1Stability AI, 2Northeastern University
*Equal contribution ^Equal advising
        

SV4D takes a reference video as input and generates novel view videos and 4D models.

Abstract

We present Stable Video 4D (SV4D) — a latent video diffusion model for multi-frame and multi-view consistent dynamic 3D content generation. Unlike previous methods that rely on separately trained generative models for video generation and novel view synthesis, we design a unified diffusion model to generate novel view videos of dynamic 3D objects. Specifically, given a monocular reference video, SV4D generates novel views for each video frame that are temporally consistent. We then use the generated novel view videos to optimize an implicit 4D representation (dynamic NeRF) efficiently, without the need for cumbersome SDS-based optimization used in most prior works. To train our unified novel view video generation model, we curated a dynamic 3D object dataset from the existing Objaverse dataset. Extensive experimental results on multiple datasets and user studies demonstrate SV4D’s state-of-the-art performance on novel-view video synthesis as well as 4D generation compared to prior works.

Summary Video

Results and Comparison

Novel View Video Synthesis

Comparing our results with baselines.


4D Optimization

Comparing our results with baselines.

More results generated by SV4D

BibTeX


	@article{xie2024sv4d,
	    title={{SV4D}: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency}, 
	    author={Yiming Xie and Chun-Han Yao and Vikram Voleti and Huaizu Jiang and Varun Jampani},
	    journal={arXiv preprint arXiv:2407.17470},
	    year={2024},
	}