Zobrazeno 1 - 10
of 371
pro vyhledávání: '"Ren, Wenqi"'
Image restoration has experienced significant advancements due to the development of deep learning. Nevertheless, it encounters challenges related to ill-posed problems, resulting in deviations between single model predictions and ground-truths. Ense
Externí odkaz:
http://arxiv.org/abs/2410.22959
Visual language pre-training (VLP) models have demonstrated significant success across various domains, yet they remain vulnerable to adversarial attacks. Addressing these adversarial vulnerabilities is crucial for enhancing security in multimodal le
Externí odkaz:
http://arxiv.org/abs/2410.04884
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 methods still face two challenges: the requirement for dozens of sampling st
Externí odkaz:
http://arxiv.org/abs/2409.17058
Blind face restoration endeavors to restore a clear face image from a degraded counterpart. Recent approaches employing Generative Adversarial Networks (GANs) as priors have demonstrated remarkable success in this field. However, these methods encoun
Externí odkaz:
http://arxiv.org/abs/2409.00991
Publikováno v:
IEEE Transactions on Intelligent Transportation Systems, 2024
The visible-light camera, which is capable of environment perception and navigation assistance, has emerged as an essential imaging sensor for marine surface vessels in intelligent waterborne transportation systems (IWTS). However, the visual imaging
Externí odkaz:
http://arxiv.org/abs/2409.01500
Existing deraining Transformers employ self-attention mechanisms with fixed-range windows or along channel dimensions, limiting the exploitation of non-local receptive fields. In response to this issue, we introduce a novel dual-branch hybrid Transfo
Externí odkaz:
http://arxiv.org/abs/2409.00410
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 fixed-range blocks to reduce computational load. However, such a compro
Externí odkaz:
http://arxiv.org/abs/2407.10172
Multi-view counting (MVC) methods have shown their superiority over single-view counterparts, particularly in situations characterized by heavy occlusion and severe perspective distortions. However, hand-crafted heuristic features and identical camer
Externí odkaz:
http://arxiv.org/abs/2407.02047
Object detection techniques for Unmanned Aerial Vehicles (UAVs) rely on Deep Neural Networks (DNNs), which are vulnerable to adversarial attacks. Nonetheless, adversarial patches generated by existing algorithms in the UAV domain pay very little atte
Externí odkaz:
http://arxiv.org/abs/2405.07595
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 prior knowledge, struggle to effectively address a wide range of adversar
Externí odkaz:
http://arxiv.org/abs/2404.16452