Tutorial

Optics for Better AI: Capturing and Synthesizing Realistic Data for Low-light Enhancement

Yinqiang Zheng · Yunhao Zou · Haiyang Jiang · Ying Fu

West 114 - 115
[ Abstract ] [ Project Page ]
Mon 19 Jun 9 a.m. PDT — noon PDT

Abstract:

This half-day tutorial will cover the latest advances in the broad theme of Optics for Better AI, with a specific focus on how to capture and synthesize realistic data for training low-light enhancement deep models. In this tutorial, we will first present the overall pipeline and effects of using realistic data, including (i) Low-light Image Enhancement using Synthesized Data; (ii) Low-light Video Enhancement using Captured Data. Then, we show detailed instructions on noise calibration and construction of optical imaging systems, including (iii) How to Calibrate the Noise Model of a Specific Camera; (iv) How to Construct a Co-axial Imaging System.

Chat is not available.