17 papers
DVFace: Spatio-Temporal Dual-Prior Diffusion for Video Face Restoration
Zheng Chen, Bowen Chai, Rongjun Gao +7
Video face restoration aims to enhance degraded face videos into high-quality results with realistic facial details, stable identity, and temporal coherence. Recent diffusion-based…
The Fourth Challenge on Image Super-Resolution (4) at NTIRE 2026: Benchmark Results and Method Overview
Zheng Chen, Kai Liu, Jingkai Wang +150
This paper presents the NTIRE 2026 image super-resolution (4) challenge, one of the associated competitions of the NTIRE 2026 Workshop at CVPR 2026. The challenge aims to r…
LCUDiff: Latent Capacity Upgrade Diffusion for Faithful Human Body Restoration
Jue Gong, Zihan Zhou, Jingkai Wang +4
Existing methods for restoring degraded human-centric images often struggle with insufficient fidelity, particularly in human body restoration (HBR). Recent diffusion-based restora…
Light Up Your Face: A Physically Consistent Dataset and Diffusion Model for Face Fill-Light Enhancement
Jue Gong, Zihan Zhou, Jingkai Wang +3
Face fill-light enhancement (FFE) brightens underexposed faces by adding virtual fill light while keeping the original scene illumination and background unchanged. Most face religh…
Combined Flicker-banding and Moire Removal for Screen-Captured Images
Libo Zhu, Zihan Zhou, Zhiyi Zhou +5
Capturing display screens with mobile devices has become increasingly common, yet the resulting images often suffer from severe degradations caused by the coexistence of moiré patt…
VEQ: Modality-Adaptive Quantization for MoE Vision-Language Models
Guangshuo Qin, Zhiteng Li, Zheng Chen +3
Mixture-of-Experts(MoE) Vision-Language Models (VLMs) offer remarkable performance but incur prohibitive memory and computational costs, making compression essential. Post-Training…