In this line of work, we develop template-based methods to infer the 3D shape of surfaces from single images. We applied these monocular reconstruction methods to reconstruct the dynamics of diverse objects, for instance, baseballs, sails, and garment.
Click on the images to jump to corresponding results.Starting from our earlier approach to fast keypoint matching, we developed real-time techniques to detect deformable surfaces. Using wide-baseline correspondences between an input image and a model image, we recover quickly and accurately the 2D or 3D shape of a deforming surface. In addition, we also model (…)
AbstractRecovering the 3D shape of a nonrigid surface from a single viewpoint is known to be both ambiguous and challenging. Resolving the ambiguities typically requires prior knowledge about the most likely deformations that the surface may undergo.Here we extend theLaplacian formalism, which was first introduced inthe Graphics community to regularize 3D meshes, to achieve this (…)