Flex-DDCM adapts zero-shot image compression with diffusion guidance
Task guidance is embedded in the compressed trajectory without extra decoding complexity.
3 stories, newest first · one card per story
Task guidance is embedded in the compressed trajectory without extra decoding complexity.
AFP-GIC uses frozen AdaCode priors for controllable image compression with lower latency than DC-VIC.
FMSGOC uses vision-language foundation model priors plus diffusion reconstruction to enable generalizable semantic communication at 0.039 bits per pixel for 6G.
Today 1.5K readers · 2.4K views · 754 reads · all time 189K views