Reconstructing the shape and appearance of real-world objects using measured 2D images has been a long-standing inverse rendering problem. In this paper, we introduce new analysis-by-synthesis technique capable producing high-quality reconstructions through robust coarse-to-fine optimization physics-based differentiable rendering. Unlike most previous methods that handle geometry reflectance la...

We develop a framework for 3–D shape and motion recovery of articulated deformable objects. We propose a formalism that incorporates the use of implicit surfaces into earlier robotics approaches that were designed to handle articulated structures. We demonstrate its effectiveness for human body modeling from video sequences. Our method is both robust and generic. It could easily be applied to o...

We develop a framework for 3–D shape and motion recovery of articulated deformable objects. We propose a formalism that incorporates the use of implicit surfaces into earlier robotics approaches that were designed to handle articulated structures. We demonstrate its effectiveness for human body modeling from synchronized video sequences. Our method is both robust and generic. It could easily be...

Estimating the structure of the human face is a long studied and difficult task. In this paper we present a new method for estimating facial structure from only a minimal number of salient feature points. The presented method uses the Extended Kalman Filter (EKF) to regress 3D Morphable Model (3DMM) shape parameters and solve rigid body motion using a simplified camera model. A linear method fo...

A shape recovery problem of book surface using two shade images under the fully perspective environments is discussed. In order to simplify the problem, the whole recovery process is divided into three sequential and explicit steps: preprocessing, apparent shape recovery, and generation of ortho-image. The separation of albedo and shading with reduced e ect of interre ections is done in preproc...