Presentation / Installation
Random-access Neural Compression of Material Textures
SessionPapers Fast Forward
DescriptionThis work introduces a neural compression technique for mipmapped material texture sets, offering significantly better compression than BCx at comparable quality and even surpassing entropy-coded AVIF and JPEG XL at low bitrates. Our method uses small, optimized neural networks for efficient compression, real-time decompression, and random access on GPUs.
Event Type
Technical Paper
TimeSunday, 6 August 20236pm - 8:30pm PDT
LocationWest Hall B
ACM Digital Library
Technical Papers pdfs
Session Time & Location
Production & Animation
Research & Education
Livestreamed
Recorded
Animation/Simulation
Artificial Intelligence/Machine Learning
Image Processing
Modeling
Rendering
Video
Virtual Reality
FC
FCS
V
VS
E
EFC
EE
