W
Wolfgang Heidrich
Researcher at King Abdullah University of Science and Technology
Publications - 336
Citations - 18089
Wolfgang Heidrich is an academic researcher from King Abdullah University of Science and Technology. The author has contributed to research in topics: Rendering (computer graphics) & Pixel. The author has an hindex of 64, co-authored 312 publications receiving 15854 citations. Previous affiliations of Wolfgang Heidrich include University of Erlangen-Nuremberg & Nvidia.
Papers
More filters
Journal ArticleDOI
Imaging in scattering media using correlation image sensors and sparse convolutional coding
TL;DR: A new convolutional sparse coding approach for recovering transient (light-in-flight) images from correlation image sensors and the derivation of a new physically-motivated model for transient images with drastically improved sparsity is presented.
Patent
Electronic camera having multiple sensors for capturing high dynamic range images and related methods
TL;DR: In this paper, the authors present a controller for controlling the shutter and the readout circuitry of an electronic camera consisting of a processor and a memory having computer-readable code embodied therein which, when executed by the processor, causes the controller to open the shutter for an image capture period to allow the two or more image sensor arrays to capture pixel data.
Proceedings ArticleDOI
Tomographic reconstruction of transparent objects
TL;DR: This work presents a visible light tomographic reconstruction method for recovering the shape of transparent objects, such as glass, which is relatively simple to implement, and accounts for refraction, which can be a significant problem invisible light tomography.
Journal ArticleDOI
Cloth Motion Capture
TL;DR: A novel seed‐and‐grow approach is described to adapt the SIFT algorithm to deformable geometry, and feature points are interpolated to parameterise the complete geometry.
Proceedings ArticleDOI
Deep End-to-End Time-of-Flight Imaging
TL;DR: It is demonstrated that the proposed network can efficiently exploit the spatio-temporal structures of ToF frequency measurements, and validate the performance of the joint multipath removal, denoising and phase unwrapping method on a wide range of challenging scenes.