SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency
This addresses the challenge of creating consistent dynamic 3D objects for applications like virtual reality or animation, representing an incremental improvement over prior methods that used separate models.
The paper tackles the problem of generating dynamic 3D content from monocular videos by introducing SV4D, a unified diffusion model that produces novel view videos with multi-frame and multi-view consistency, achieving state-of-the-art performance in novel-view video synthesis and 4D generation as validated by experiments and user studies.
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.