O
Orazio Gallo
Researcher at Nvidia
Publications - 70
Citations - 4445
Orazio Gallo is an academic researcher from Nvidia. The author has contributed to research in topics: View synthesis & Image processing. The author has an hindex of 22, co-authored 68 publications receiving 3018 citations. Previous affiliations of Orazio Gallo include Smith-Kettlewell Institute & University of California, Santa Cruz.
Papers
More filters
Journal ArticleDOI
Loss Functions for Image Restoration With Neural Networks
TL;DR: It is shown that the quality of the results improves significantly with better loss functions, even when the network architecture is left unchanged, and a novel, differentiable error function is proposed.
Journal ArticleDOI
FlexISP: a flexible camera image processing framework
Felix Heide,Markus Steinberger,Yun-Ta Tsai,Mushfiqur Rouf,Dawid Pająk,Dikpal Reddy,Orazio Gallo,Jing Liu,Wolfgang Heidrich,Karen Egiazarian,Jan Kautz,Kari Pulli +11 more
TL;DR: This work proposes an end-to-end system that is aware of the camera and image model, enforces natural-image priors, while jointly accounting for common image processing steps like demosaicking, denoising, deconvolution, and so forth, all directly in a given output representation.
Proceedings ArticleDOI
Artifact-free High Dynamic Range imaging
TL;DR: This work presents a technique capable of dealing with a large amount of movement in the scene: it finds, in all the available exposures, patches consistent with a reference image previously selected from the stack and generates the HDR image by averaging the radiance estimates of all such regions.
Proceedings ArticleDOI
HDR Deghosting: How to Deal with Saturation?
TL;DR: A novel method for aligning images in an HDR (high-dynamic-range) image stack to produce a new exposure stack where all the images are aligned and appear as if they were taken simultaneously, even in the case of highly dynamic scenes.
Posted Content
Loss Functions for Neural Networks for Image Processing
TL;DR: It is shown that the quality of the results improves significantly with better loss functions, even when the network architecture is left unchanged, and a novel, differentiable error function is proposed.