Proposes generative compression with WGAN and diffusion models for perception-based denoising, plus non-asymptotic error bounds under Gaussian noise.
The open images dataset v4: Unified image classification, object detec- tion, and visual relationship detection at scale,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Perception-based Image Denoising via Generative Compression
Proposes generative compression with WGAN and diffusion models for perception-based denoising, plus non-asymptotic error bounds under Gaussian noise.