Presentation
Rigidity-Aware 3D Gaussian Deformation from a Single Image
DescriptionReconstructing 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 a Gaussian-to-Pixel Matching that bridges the domain gap between 3D Gaussian representations and 2D pixel observations. This enables robust deformation guidance from sparse visual cues. Second, we propose novel Rigid Part Segmentation consisting of initialization and refinement steps. 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 limited input. Extensive experiments demonstrate that our approach significantly outperforms existing methods, particularly in deformation accuracy and geometric preservation. Furthermore, our framework naturally extends to various applications, such as frame interpolation and interactive object manipulation.
Event Type
Technical Papers
TimeThursday, 18 December 202510:50am - 11:01am HKT
LocationMeeting Room S426+S427, Level 4