Lions and Tigers and Bears: Capturing Non-Rigid, 3D, Articulated Shape from Images
نویسندگان
چکیده
Animals are widespread in nature and the analysis of their shape and motion is important in many fields and industries. Modeling 3D animal shape, however, is difficult because the 3D scanning methods used to capture human shape are not applicable to wild animals or natural settings. Consequently, we propose a method to capture the detailed 3D shape of animals from images alone. The articulated and deformable nature of animals makes this problem extremely challenging, particularly in unconstrained environments with moving and uncalibrated cameras. To make this possible, we use a strong prior model of articulated animal shape that we fit to the image data. We then deform the animal shape in a canonical reference pose such that it matches image evidence when articulated and projected into multiple images. Our method extracts significantly more 3D shape detail than previous methods and is able to model new species, including the shape of an extinct animal, using only a few video frames. Additionally, the projected 3D shapes are accurate enough to facilitate the extraction of a realistic texture map from multiple frames.
منابع مشابه
Combined discriminative and generative articulated pose and non-rigid shape estimation
Estimation of three-dimensional articulated human pose and motion from images is a central problem in computer vision. Much of the previous work has been limited by the use of crude generative models of humans represented as articulated collections of simple parts such as cylinders. Automatic initialization of such models has proved difficult and most approaches assume that the size and shape o...
متن کاملArticulated and Elastic Non-rigid Motion: A Review
Motion of physical objects is non-rigid, in general. Most researchers have focused on the study of the motion and structure of rigid objects because of its simplicity and elegance. Recently, investigation of non-rigid structure and motion transformation has drawn the attention of researchers from a wide spectrum of disciplines. Since the non-rigid motion class encompasses a huge domain, we rest...
متن کاملRecovering Articulated Non-rigid Shapes, Motions and Kinematic Chains from Video
JINGYU YAN: Recovering Articulated Non-rigid Shapes, Motions and Kinematic Chains from Video. (Under the direction of Marc Pollefeys.) Recovering articulated shape and motion, especially human body motion, from video is a challenging problem with a wide range of applications in medical study, sport analysis and animation, etc. Previous work on articulated motion recovery generally requires prio...
متن کامل3D shape template generation from RGB-D images capturing a moving and deforming object
Automatically reconstructing a 3D shape model of a nonrigid object using a sequence from a single commodity RGB-D sensor is a challenging problem. Some techniques use a 3D shape template of a target object; however, in order to generate the template automatically, the target object required to be stationary. Otherwise, a non-rigid ICP algorithm, which registers a pair of point clouds, can be us...
متن کامل