Reconstructing Complete 3D Models from Single Images (Talk)
We present an approach to creating 3D models of objects depicted in Web images, even when each object may only be shown in a single image. Our approach uses a comparatively small collection of existing 3D models to guide the reconstruction process. These existing shapes are used to derive information about shape structure. Our guiding idea is to jointly analyze the images and the available 3D models. Joint analysis of all images along with the available shapes regularizes the formulated optimization problems, stabilizes estimation of camera parameters and construction of dense pixel-level correspondences, and leads to reasonable reproduction of object appearance in the absence of traditional multi-view cues. Joint work with Qixing Huang and Hai Wang.
Biography: Vladlen Koltun is the director of the Visual Computing Lab at Intel Labs. Works in computer vision, computer graphics, and machine learning. Received a PhD in 2002 for new results in theoretical computational geometry. Spent three years at UC Berkeley as a postdoc in the theory group. Joined the Stanford Computer Science department in 2005 as a full-time faculty member working in theoretical computer science. Switched to applied research in visual computing in 2007. Joined Intel Labs in 2015.