6 papers
Spectral and Trajectory Regularization for Diffusion Transformer Super-Resolution
Jingkai Wang, Yixin Tang, Jue Gong +6
Diffusion transformer (DiT) architectures show great potential for real-world image super-resolution (Real-ISR). However, their computationally expensive iterative sampling necessi…
DenoiseGS: Gaussian Reconstruction Model for Burst Denoising
Yongsen Cheng, Yuanhao Cai, Yulun Zhang
Burst denoising methods are crucial for enhancing images captured on handheld devices, but they often struggle with large motion or suffer from prohibitive computational costs. In…
Measurement-Constrained Sampling for Text-Prompted Blind Face Restoration
Wenjie Li, Yulun Zhang, Guangwei Gao +2
Blind face restoration (BFR) may correspond to multiple plausible high-quality (HQ) reconstructions under extremely low-quality (LQ) inputs. However, existing methods typically pro…
Flow-Matching Guided Deep Unfolding for Hyperspectral Image Reconstruction
Yi Ai, Yuanhao Cai, Yulun Zhang +2
Reconstructing a three-dimensional hyperspectral cube from a two-dimensional compressed measurement is a severely ill-posed inverse problem. Existing deep unfolding networks (DUNs)…
DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup Tables
Sidi Yang, Binxiao Huang, Yulun Zhang +3
While deep neural networks have revolutionized image denoising capabilities, their deployment on edge devices remains challenging due to substantial computational and memory requir…
Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal
Yijun Yang, Hongtao Wu, Angelica I. Aviles-Rivero +3
Real-world vision tasks frequently suffer from the appearance of unexpected adverse weather conditions, including rain, haze, snow, and raindrops. In the last decade, convolutional…