We introduce an algorithm for high-quality, interactive light field rendering from only a small number of input images with dense depth information. The algorithm bridges the gap ...
Hartmut Schirmacher, Wolfgang Heidrich, Hans-Peter...
This paper investigates segmentation-based image descriptors for object category recognition. In contrast to commonly used interest points the proposed descriptors are extracted f...
We present a novel multi-baseline, multi-resolution stereo method, which varies the baseline and resolution proportionally to depth to obtain a reconstruction in which the depth e...
David Gallup, Jan-Michael Frahm, Philippos Mordoha...
We propose methods to super-resolve compressed video sequences that may consist of frames with missing blocks of pixels in addition to compression artifacts. Different from tradit...
Abstract. We present a closed-form solution to the problem of recovering the 3D shape of a non-rigid inelastic surface from 3D-to-2D correspondences. This lets us detect and recons...
Mathieu Salzmann, Francesc Moreno-Noguer, Vincent ...