Shift-Window Meets Dual Attention: A Multi-Model Architecture for Specular Highlight Removal
College of Mechanical and Vehicle Engineering, Chongqing University(重庆大学机械与车辆工程学院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);Artificial Intelligence Center, Geely Automotive Research Institute(吉利汽车研究院人工智能中心)
Tianci Huo, Lingfeng Qi, Yuhan Chen, Qihong Xue, Jinyuan Shao, Hai Yu, Jie Li, Zhanhua Zhang, Guofa Li
Inevitable specular highlights in practical environments severely impair the visual performance, thus degrading the task effectiveness and efficiency. Although there exist considerable methods that focus on local information from convolutional neural network models or global information from transformer models, the single-type model falls into a modeling dilemma between local fine-grained details and global long-range dependencies, thus deteriorating for specular highlights with different scales. Therefore, to accommodate specular highlights of all scales, we propose a multi-model architecture for specular highlight removal (MM-SHR) that effectively captures fine-grained features in highlight regions and models long-range dependencies between highlight and highlight-free areas. Specifically, we employ convolution operations to extract local details in the shallow layers of MM-SHR, and utilize the attention mechanism to capture global features in the deep layers, ensuring both operation efficiency and removal accuracy. To model long-range dependencies without compromising computational complexity, we utilize a coarse-to-fine manner and propose Omni-Directional Attention Integration Block(OAIBlock) and Adaptive Region-Aware Hybrid-Domain Dual Attention Convolutional Network(HDDAConv) , which leverage omni-directiona pixel-shifting and window-dividing operations at the raw features to achieve specular highlight removal. Extensive experimental results on three benchmark tasks and six types of surface materials demonstrate that MM-SHR outperforms state-of-the-art methods in both accuracy and efficiency for specular highlight removal. The implementation will be made publicly available at https://github.com/Htcicv/MM-SHR.
Dual-Hybrid Attention Network for Specular Highlight Removal
University of Macau(澳门大学);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Baoshan University(保山学院);Huizhou University(惠州学院)
Towards High-Quality Specular Highlight Removal by Leveraging Large-Scale Synthetic Data
The Hong Kong Polytechnic University(香港理工大学);Sun Yat-sen University(中山大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Hong Kong University of Science and Technology(香港科技大学);Wuhan University(武汉大学)
Learning to Remove Wrinkled Transparent Film with Polarized Prior
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));SmartMore Corporation(旷世科技公司);Zhejiang University(浙江大学);Zhejiang Lab(浙江大学实验室)
Single Document Image Highlight Removal via A Large-Scale Real-World Dataset and A Location-Aware Network
College of Computer Science, Jilin University(吉林大学计算机科学学院);Institute of Information Science, Academia Sinica(中国科学院信息科学研究院);National Yang Ming Chiao Tung University(阳明交通大学);National Taiwan University(台湾大学)
A Highlight Removal Method for Capsule Endoscopy Images
School of Artificial Intelligence and Computer Science, Jiangnan University(江南大学人工智能与计算机学院);Engineering Research Center of Intelligent Technology for Healthcare, Ministry of Education(教育部智慧医疗技术工程研究中心)
When A Conventional Filter Meets Deep Learning: Basis Composition Learning on Image Filters
Hong Kong Metropolitan University(香港都会大学);Nanjing University of Aeronautics and Astronautics(南京航空航天大学);Lingnan University(岭南大学);Education University of Hong Kong(香港教育大学)
WeatherRemover: All-in-one Adverse Weather Removal with Multi-scale Feature Map Compression
Guangdong University of Technology(广东工业大学);Sanda University(上海杉达学院);University of Queensland(昆士兰大学);Shenzhen MSU-BIT University(深圳北理莫斯科大学);Zhejiang college of Security Technology(浙江安防职业技术学院);Northwest China Research Institute of Electronic Equipment(西北电子设备研究所);Shenzhen Research Institute of Big Data(深圳市大数据研究院);Shenzhen University(深圳大学);Misr Higher Institute for Commerce and Computers(米斯尔商业与计算机高等学院)