SkeletonGaussian: Editable 4D Generation through Gaussian Skeletonization
This addresses the need for more interpretable and editable motion representation in 4D generation for applications like animation and virtual reality.
The paper tackled the problem of limited control and editability in 4D generation by proposing SkeletonGaussian, a framework for generating editable dynamic 3D Gaussians from monocular video, which surpassed existing methods in quality and enabled intuitive motion editing.
4D generation has made remarkable progress in synthesizing dynamic 3D objects from input text, images, or videos. However, existing methods often represent motion as an implicit deformation field, which limits direct control and editability. To address this issue, we propose SkeletonGaussian, a novel framework for generating editable dynamic 3D Gaussians from monocular video input. Our approach introduces a hierarchical articulated representation that decomposes motion into sparse rigid motion explicitly driven by a skeleton and fine-grained non-rigid motion. Concretely, we extract a robust skeleton and drive rigid motion via linear blend skinning, followed by a hexplane-based refinement for non-rigid deformations, enhancing interpretability and editability. Experimental results demonstrate that SkeletonGaussian surpasses existing methods in generation quality while enabling intuitive motion editing, establishing a new paradigm for editable 4D generation. Project page: https://wusar.github.io/projects/skeletongaussian/