15 citations · 30 across the 14 of their papers we have counts for
14 papers · 1 filter
Ultra-High-Definition Restoration Transformers with Correlation Matching Transformation
Cong Wang, Liyan Wang, Jinshan Pan +4
We propose UHDformer++, a general Transformer-based framework to solve numerous Ultra-High-Definition (UHD) image restoration tasks. UHDformer++ operates across coordinated lea…
Timestep Rescheduling in Diffusion Inversion
Shangquan Sun, Ting Gong, Zhirui Liu +5
Diffusion inversion, which maps images back to the Gaussian latent space of a diffusion model, is a critical task for image reconstruction and editing. While DDIM enables fast dete…
Learning Spatially Adaptive Structural Coordination for Underwater Salient Object Detection
Lin Hong, Chenhui Wang, Linan Deng +6
Underwater salient object detection (USOD) has attracted increasing attention for underwater scene understanding and vision-guided robotic applications. However, the spatially non-…
CAMotion: A High-Quality Benchmark for Camouflaged Moving Object Detection in the Wild
Siyuan Yao, Hao Sun, Ruiqi Yu +3
Discovering camouflaged objects is a challenging task in computer vision due to the high similarity between camouflaged objects and their surroundings. While the problem of camoufl…
UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extraction
Siyuan Yao, Dongxiu Liu, Taotao Li +3
Building extraction from remote sensing images is a challenging task due to the complex structure variations of the buildings. Existing methods employ convolutional or self-attenti…
UncTrack: Reliable Visual Object Tracking with Uncertainty-Aware Prototype Memory Network
Siyuan Yao, Yang Guo, Yanyang Yan +2
Transformer-based trackers have achieved promising success and become the dominant tracking paradigm due to their accuracy and efficiency. Despite the substantial progress, most of…
EnsIR: An Ensemble Algorithm for Image Restoration via Gaussian Mixture Models
Shangquan Sun, Wenqi Ren, Zikun Liu +3
Image restoration has experienced significant advancements due to the development of deep learning. Nevertheless, it encounters challenges related to ill-posed problems, resulting…
Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors
Aiping Zhang, Zongsheng Yue, Renjing Pei +2
Diffusion-based image super-resolution (SR) methods have achieved remarkable success by leveraging large pre-trained text-to-image diffusion models as priors. However, these method…
A Hybrid Transformer-Mamba Network for Single Image Deraining
Shangquan Sun, Wenqi Ren, Juxiang Zhou +3
Existing deraining Transformers employ self-attention mechanisms with fixed-range windows or along channel dimensions, limiting the exploitation of non-local receptive fields. In r…
Restoring Images in Adverse Weather Conditions via Histogram Transformer
Shangquan Sun, Wenqi Ren, Xinwei Gao +2
Transformer-based image restoration methods in adverse weather have achieved significant progress. Most of them use self-attention along the channel dimension or within spatially f…
PAD: Patch-Agnostic Defense against Adversarial Patch Attacks
Lihua Jing, Rui Wang, Wenqi Ren +2
Adversarial patch attacks present a significant threat to real-world object detectors due to their practical feasibility. Existing defense methods, which rely on attack data or pri…
DI-Retinex: Digital-Imaging Retinex Theory for Low-Light Image Enhancement
Shangquan Sun, Wenqi Ren, Jingyang Peng +2
Many existing methods for low-light image enhancement (LLIE) based on Retinex theory ignore important factors that affect the validity of this theory in digital imaging, such as no…
How Powerful Potential of Attention on Image Restoration?
Cong Wang, Jinshan Pan, Yeying Jin +5
Transformers have demonstrated their effectiveness in image restoration tasks. Existing Transformer architectures typically comprise two essential components: multi-head self-atten…
Logit Standardization in Knowledge Distillation
Shangquan Sun, Wenqi Ren, Jingzhi Li +2
Knowledge distillation involves transferring soft labels from a teacher to a student using a shared temperature-based softmax function. However, the assumption of a shared temperat…