If you missed SIGGRAPH 2017 watch a selection of recorded Live Streaming Sessions.
If you missed SIGGRAPH 2017 watch a selection of recorded Live Streaming Sessions.
This paper presents an interactive method to create visually plausible relighting results from one photograph by estimating and reconstructing the pseudo-3D scene with a top-down approach.
Jung-Hsuan Wu
Tokyo Institute of Technology
Suguru Saito
Tokyo Institute of Technology
This general and efficient framework for non-uniform light-field warping with 4D patch matching is used for panorama light-field imaging, light-field retargeting, and artistic manipulation of light fields.
Clemens Birklbauer
Johannes Kepler Universität Linz, DAQRI
David Schedl
Johannes Kepler Universität Linz
Oliver Bimber
Johannes Kepler Universität Linz
This machine-learning approach to generate a high-quality HDR image from a set of bracketed exposure images delivers significant improvement over state-of-the-art approaches.
Nima Khademi Kalantari
University of California, San Diego
Ravi Ramamoorthi
University of California, San Diego
This image-downscaling technique is capable of appropriately representing high-frequency structured patterns. It creates more faithful representations of the original content, retaining visually important details that would otherwise be lost, or subject to undesirable aliasing artifacts.
Eduardo Gastal
Universidade Federal do Rio Grande do Sul
Manuel Oliveira
Universidade Federal do Rio Grande do Sul
This method formulates illumination transfer between portrait photographs as a geometry-aware color mapping solved by mass transport. It can be used for creative lighting design for portraits.
Zhixin Shu
Stony Brook University
Sunil Hadap
Adobe Research
Eli Shechtman
Adobe Research
Kalyan Sunkavalli
Adobe Research
Sylvain Paris
Adobe Research
Dimitris Samaras
Stony Brook University