Extensive experiments across multiple tasks and challenging domain shifts demonstrate that DCTTA consistently outperforms state-of-the-art AiOIR baselines, achieving up to +4.57 dB PSNR improvement on the Rain100H dataset.
FIT employs a lightweight Degradation Encoder to predict a global degradation vector and a spatial degradation map from local degradation severity, which jointly condition the patch embedding and unembedding through adaptive deformation, and introduces a task-token dropout strategy that regularizes task conditioning du...
Zi-Hao He, Yunfeng Wu, Xinchao Wang et al.· 0 citations
This work proposes FaverNet, a Frequency-guided All-in-one VidEo Restoration Network, which incorporates a Frequency-discriminative Conditioning Mechanism (FCM) and a Prompt-guided Alignment Mechanism (PAM), which enhances the degradation-awareness of the restoration process by conditioning the model with degradation c...
Haiyu Zhao, Yuanbiao Gou, Boyun Li et al.· International Journal of Com...· 0 citations
All-in-one Image Restoration (AIR) seeks to address diverse degradations using a unified model trained only once. Existing methods often rely on degradation-specific guidance, leading to conflicting gradients during training. In contrast, diffusion models offer a promising alternative by operating in a high-noise space...
Jia-Wei Wu, Luwei Tu, Zhe Wang et al.· IEEE Transactions on Image P...· 0 citations
MGN-AIR is presented, a novel pixel-level restoration framework for all-in-one image restoration that leverages both textual and visual prompts to provide global and local degradation cues, guiding the model on where to look and how to restore at each pixel.
Chun-Xiao Liu, Wei Liu, Anbin Xiong et al.· 0 citations
QuReC, a unified framework for all-in-one image restoration, consists of a Degradation-Guided Query Reconstruction Module (DQRM) and a Local-Global Response Calibration Module (LGRCM), which provides fine-grained spatially adaptive restoration guidance.
Blind Image Quality Assessment (BIQA) models trained on one distortion distribution often degrade when exposed to new ones, making sequential adaptation without forgetting a fundamental challenge. While continual learning offers a natural solution, existing methods typically retrain the entire backbone per task, limiti...
Satish Maurya, Parimala Kancharla· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.