10 citations · 11 across the 18 of their papers we have counts for
9 papers · 1 filter
RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restoration
Zilong Zhang, Chujie Qin, Chunle Guo +4
This work presents Robust Representation Learning via Adaptive Mask (RAM++), a two-stage framework for all-in-one image restoration. RAM++ integrates high-level semantic understand…
ViDA-UGC: Detailed Image Quality Analysis via Visual Distortion Assessment for UGC Images
Wenjie Liao, Jieyu Yuan, Yifang Xu +8
Recent advances in Multimodal Large Language Models (MLLMs) have introduced a paradigm shift for Image Quality Assessment (IQA) from unexplainable image quality scoring to explaina…
TimeMachine: Fine-Grained Facial Age Editing with Identity Preservation
Yilin Mi, Qixin Yan, Zheng-Peng Duan +5
With the advancement of generative models, facial image editing has made significant progress. However, achieving fine-grained age editing while preserving personal identity remain…
Incorporating Uncertainty-Guided and Top-k Codebook Matching for Real-World Blind Image Super-Resolution
Weilei Wen, Tianyi Zhang, Qianqian Zhao +4
Recent advancements in codebook-based real image super-resolution (SR) have shown promising results in real-world applications. The core idea involves matching high-quality image f…
A Systematic Investigation on Deep Learning-Based Omnidirectional Image and Video Super-Resolution
Qianqian Zhao, Chunle Guo, Tianyi Zhang +5
Omnidirectional image and video super-resolution is a crucial research topic in low-level vision, playing an essential role in virtual reality and augmented reality applications. I…
DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data
Ruiqi Wu, Xinjie Wang, Liu Liu +6
We present DIPO, a novel framework for the controllable generation of articulated 3D objects from a pair of images: one depicting the object in a resting state and the other in an…
NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment
Shuhao Han, Haotian Fan, Fangyuan Kong +112
This paper reports on the NTIRE 2025 challenge on Text to Image (T2I) generation model quality assessment, which will be held in conjunction with the New Trends in Image Restoratio…
3D-UIR: 3D Gaussian for Underwater 3D Scene Reconstruction via Physics Based Appearance-Medium Decoupling
Jieyu Yuan, Yujun Li, Yuanlin Zhang +4
Novel view synthesis for underwater scene reconstruction presents unique challenges due to complex light-media interactions. Optical scattering and absorption in water body bring i…
Classic Video Denoising in a Machine Learning World: Robust, Fast, and Controllable
Xin Jin, Simon Niklaus, Zhoutong Zhang +5
Denoising is a crucial step in many video processing pipelines such as in interactive editing, where high quality, speed, and user control are essential. While recent approaches ac…