5 papers
DriftSR: One-Step Real-World Image Super-Resolution via Distribution Drifting
Wei Zhu, Kai Zhang, Yu Zheng +4
One-step real-world image super-resolution (Real-ISR) offers efficient inference, but recovering realistic and perceptually rich details often relies on score distillation or adver…
Noise-Started One-Step Real-World Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement
Wei Zhu, Kai Zhang, Yu Zheng +3
Pre-trained text-to-image (T2I) diffusion models have shown strong potential for real-world image super-resolution (Real-ISR), owing to their noise-started generation process that…
DRNet: All-in-One Image Restoration via Prior-Guided Dynamic Reparameterization
Ao Li, Xiaoning Liu, Sheng Li +5
All-in-one image restoration aims to handle diverse degradations within a single model. However, existing methods often suffer from three key limitations: 1) per-input computationa…
UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model
Shuai Yuan, Lei Luo, Zhuo Hui +4
Traditional unsupervised optical flow methods are vulnerable to occlusions and motion boundaries due to lack of object-level information. Therefore, we propose UnSAMFlow, an unsupe…
Training Neural Networks on RAW and HDR Images for Restoration Tasks
Andrew Yanzhe Ke, Lei Luo, Xiaoyu Xiang +4
The vast majority of standard image and video content available online is represented in display-encoded color spaces, in which pixel values are conveniently scaled to a limited ra…