ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
This addresses the limitation of dense multi-view captures in neural 3D reconstruction for broader applications like immersive experiences and scene-level text-to-3D generation, representing a novel method for a known bottleneck.
The paper tackles the problem of synthesizing high-fidelity novel views from single or sparse images by proposing ViewCrafter, which leverages video diffusion models and point-based representations to achieve precise camera pose control and superior performance in experiments.
Despite recent advancements in neural 3D reconstruction, the dependence on dense multi-view captures restricts their broader applicability. In this work, we propose \textbf{ViewCrafter}, a novel method for synthesizing high-fidelity novel views of generic scenes from single or sparse images with the prior of video diffusion model. Our method takes advantage of the powerful generation capabilities of video diffusion model and the coarse 3D clues offered by point-based representation to generate high-quality video frames with precise camera pose control. To further enlarge the generation range of novel views, we tailored an iterative view synthesis strategy together with a camera trajectory planning algorithm to progressively extend the 3D clues and the areas covered by the novel views. With ViewCrafter, we can facilitate various applications, such as immersive experiences with real-time rendering by efficiently optimizing a 3D-GS representation using the reconstructed 3D points and the generated novel views, and scene-level text-to-3D generation for more imaginative content creation. Extensive experiments on diverse datasets demonstrate the strong generalization capability and superior performance of our method in synthesizing high-fidelity and consistent novel views.