Presentation / Installation
HiGAN+: Handwriting Imitation GAN With Disentangled Representations
SessionMagical Sketching
DescriptionWhile this task is challenging for machines, humans can quickly learn handwriting imitation with hallucinations. Humans can imitate handwriting perhaps because they can learn to disentangle textual contents and calligraphic styles. Inspired by this, we propose HiGAN+ for realistic handwritten text synthesis based on disentangled representations, achieving the state-of-the-art performance.
Event Type
Technical Paper
TimeMonday, 7 August 20233:45pm - 3:56pm PDT
LocationPetree Hall C
ACM Digital Library
Technical Papers pdfs
Session Time & Location
Research & Education
Livestreamed
Recorded
Image Processing
Video
FC
FCS
V
VS
EFC