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

TL;DR

SV4D introduces a unified diffusion model that generates temporally consistent multi-view videos of dynamic 3D objects from a single monocular video, enabling efficient 4D content creation.

Contribution

We propose a novel latent diffusion approach for joint multi-frame and multi-view consistent 3D content generation, unifying video synthesis and view synthesis tasks.

Findings

Achieves state-of-the-art results on novel-view video synthesis

Enables efficient 4D dynamic object representation without heavy optimization

Demonstrates high-quality, temporally consistent multi-view videos

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 curate 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.