"Generative adversarial networks"

Realistic Talking Face Synthesis With Geometry-Aware Feature Transformation

Recent studies have shown remarkable success in synthesizing realistic talking faces by exploiting generative adversarial networks. However, existing methods are mostly target specific that cannot generate images of previously unseen people, and they …

TSGAN: A Two-Stream Generative Adversarial Network for Bit-Depth Expansion

The rapid development of display devices and the continuous improvement of visual quality requirements put urgent demands on high bit-depth (HBD) image, but most legacy data are stored and transmitted at low bit-depth (LBD). Bit-depth expansion (BDE) …

Gan Based Multi-Exposure Inverse Tone Mapping

High dynamic range (HDR) imaging provide larger range of luminosity and wider color gamut than conventional low dynamic range (LDR) imaging. The method which transforms LDR contents to HDR contents is called inverse tone mapping. After deep neural …