Lions and Tigers and Bears: Capturing Non-rigid, 3D, Articulated Shape from Images
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Figure 1 : Animals from Images. We generate 3D textured articulated models of animals from images. Starting from an initial coarse shape obtained with the SMAL model , we refine the animal shape from multiple uncalibrated images and varying poses and capture a detailed texture map from multiple frames. We recover detailed 3D shapes for animal species that are in the SMAL shape space (like lions and tigers) and go beyond SMAL to capture new animals like bears. Abstract Animals are widespread
... mals 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.