WonderVerse: Extendable 3D Scene Generation with Video Generative Models
By: Hao Feng , Zhi Zuo , Jia-Hui Pan and more
Potential Business Impact:
Creates realistic, big 3D worlds from videos.
We introduce \textit{WonderVerse}, a simple but effective framework for generating extendable 3D scenes. Unlike existing methods that rely on iterative depth estimation and image inpainting, often leading to geometric distortions and inconsistencies, WonderVerse leverages the powerful world-level priors embedded within video generative foundation models to create highly immersive and geometrically coherent 3D environments. Furthermore, we propose a new technique for controllable 3D scene extension to substantially increase the scale of the generated environments. Besides, we introduce a novel abnormal sequence detection module that utilizes camera trajectory to address geometric inconsistency in the generated videos. Finally, WonderVerse is compatible with various 3D reconstruction methods, allowing both efficient and high-quality generation. Extensive experiments on 3D scene generation demonstrate that our WonderVerse, with an elegant and simple pipeline, delivers extendable and highly-realistic 3D scenes, markedly outperforming existing works that rely on more complex architectures.
Similar Papers
DeepVerse: 4D Autoregressive Video Generation as a World Model
CV and Pattern Recognition
Helps computers understand and predict how things move.
EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning
CV and Pattern Recognition
Makes one computer program edit pictures and videos.
CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition
CV and Pattern Recognition
Creates movie scenes with consistent characters and action.