Learning 3D Deformation of Animals from 2D Images

TL;DR

This paper introduces a novel volumetric deformation framework that learns to deform 3D animal models from 2D images using locally-bounded deformation energy, enabling more realistic animal model modifications.

Contribution

The paper presents a new method that jointly learns local stiffness bounds and deforms 3D models from 2D images through convex optimization, improving plausibility of animal models.

Findings

More plausible 3D animal models generated

Effective deformation of cats and horses demonstrated

Framework outperforms methods without learned stiffness

Abstract

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.