Rigidity-Aware 3D Gaussian Deformation from a Single Image
This addresses the problem of single-image deformation reconstruction for computer vision and graphics applications, representing a novel method for a known bottleneck.
The paper tackles the challenge of reconstructing object deformation from a single image by proposing DeformSplat, a framework that guides 3D Gaussian deformation using Gaussian-to-Pixel Matching and Rigid Part Segmentation, achieving significant performance improvements over existing methods.
Reconstructing object deformation from a single image remains a significant challenge in computer vision and graphics. Existing methods typically rely on multi-view video to recover deformation, limiting their applicability under constrained scenarios. To address this, we propose DeformSplat, a novel framework that effectively guides 3D Gaussian deformation from only a single image. Our method introduces two main technical contributions. First, we present Gaussian-to-Pixel Matching which bridges the domain gap between 3D Gaussian representations and 2D pixel observations. This enables robust deformation guidance from sparse visual cues. Second, we propose Rigid Part Segmentation consisting of initialization and refinement. This segmentation explicitly identifies rigid regions, crucial for maintaining geometric coherence during deformation. By combining these two techniques, our approach can reconstruct consistent deformations from a single image. Extensive experiments demonstrate that our approach significantly outperforms existing methods and naturally extends to various applications,such as frame interpolation and interactive object manipulation.