BAGS: Building Animatable Gaussian Splatting from a Monocular Video with Diffusion Priors
This work addresses the practical limitation of creating animatable 3D reconstructions from monocular videos for applications in fields like animation and virtual reality, representing an incremental improvement over existing methods.
The paper tackles the problem of constructing animatable 3D models from monocular videos, which often requires extensive view coverage and high computational costs, by proposing a method that uses 3D Gaussian Splatting and diffusion priors to accelerate training and rendering while handling limited viewpoints, achieving superior performance compared to state-of-the-art methods.
Animatable 3D reconstruction has significant applications across various fields, primarily relying on artists' handcraft creation. Recently, some studies have successfully constructed animatable 3D models from monocular videos. However, these approaches require sufficient view coverage of the object within the input video and typically necessitate significant time and computational costs for training and rendering. This limitation restricts the practical applications. In this work, we propose a method to build animatable 3D Gaussian Splatting from monocular video with diffusion priors. The 3D Gaussian representations significantly accelerate the training and rendering process, and the diffusion priors allow the method to learn 3D models with limited viewpoints. We also present the rigid regularization to enhance the utilization of the priors. We perform an extensive evaluation across various real-world videos, demonstrating its superior performance compared to the current state-of-the-art methods.