Learning 3D Deformation of Animals from 2D Images
This work addresses the challenge of realistically modifying 3D animal models for applications in graphics or animation, though it is incremental as it builds on existing deformation techniques.
The paper tackles the problem of learning 3D deformations of animals from 2D images by introducing a volumetric deformation framework with a novel locally-bounded deformation energy, which produces significantly more plausible 3D models for cats and horses compared to methods without learned stiffness.
Understanding how an animal can deform and articulate is essential for a realistic modification of its 3D model. In this paper, we show that such information can be learned from user-clicked 2D images and a template 3D model of the target animal. We present a volumetric deformation framework that produces a set of new 3D models by deforming a template 3D model according to a set of user-clicked images. Our framework is based on a novel locally-bounded deformation energy, where every local region has its own stiffness value that bounds how much distortion is allowed at that location. We jointly learn the local stiffness bounds as we deform the template 3D mesh to match each user-clicked image. We show that this seemingly complex task can be solved as a sequence of convex optimization problems. We demonstrate the effectiveness of our approach on cats and horses, which are highly deformable and articulated animals. Our framework produces new 3D models of animals that are significantly more plausible than methods without learned stiffness.