Robust Unbiased Image Synthesis

Project Details

Description

Realistic image synthesis techniques are widely used in visualization, feature film production, and other significant industries. Statistically unbiased methods are attractive from the point of view of general applicability and mathematical and algorithmic elegance. However, state of the art methods are brittle when given difficult but common inputs. This project investigates novel, dramatically more robust unbiased techniques through modern Markov Chain Monte Carlo methods.
Short titleRUIS/Lehtinen
StatusFinished
Effective start/end date01/09/201431/08/2018

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.