Realistic extreme image rescaling via generative latent space learning
Image rescaling aims to learn the optimal downscaled low-resolution (LR) image that can be
accurately reconstructed to its original high-resolution (HR) counterpart. This process is …
accurately reconstructed to its original high-resolution (HR) counterpart. This process is …
SSP-IR: Semantic and Structure Priors for Diffusion-based Realistic Image Restoration
Y Zhang, H Zhang, Z Cheng, R **e… - … on Circuits and …, 2025 - ieeexplore.ieee.org
Realistic image restoration is a crucial task in computer vision, and diffusion-based models
for image restoration have garnered significant attention due to their ability to produce …
for image restoration have garnered significant attention due to their ability to produce …
Lightweight Efficient Rate-Adaptive Network for Compression-Aware Image Rescaling
Compression-aware image rescaling approaches convert high-resolution images to
compressed low-resolution ones to fit various display devices or save bandwidth/storage …
compressed low-resolution ones to fit various display devices or save bandwidth/storage …
Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior
Compressing images at extremely low bitrates (below 0.1 bits per pixel (bpp)) is a significant
challenge due to substantial information loss. Existing extreme image compression methods …
challenge due to substantial information loss. Existing extreme image compression methods …
Re-scaling images using a SVD-based approach
M Motylinski, AJ Plater, JE Higham - Signal, Image and Video Processing, 2025 - Springer
There are many instances in computer science where computational operations must be
performed on matrices of different sizes. In the field of machine learning, particularly when …
performed on matrices of different sizes. In the field of machine learning, particularly when …