Diffusion 3D Features (Diff3F) Decorating Untextured Shapes with Distilled Semantic Features

We introduce DIFF3F, a novel feature distiller that harnesses the expressive power of inpainting diffusion features and distills them to points on 3D surfaces. Here, the proposed features are employed for point-to-point shape correspondence between assets varying in shape, pose, species, and topology. We achieve this without any fine-tuning of the underlying diffusion models, and demonstrate results on untextured meshes, point clouds, and raw scans. The leftmost mesh is the source, and all the remaining 3D shapes are targets. Note that we show raw point-to-point correspondence, without any regularization or smoothing. Inputs are point clouds, non-manifold meshes, or 2-manifold meshes. Corresponding points are similarly colored across the shapes.