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)
Gang Fu, Qing Zhang, Lei Zhu, Chunxia Xiao, Ping Li
This paper aims to remove specular highlights from a single object-level image. Although previous methods have made some progresses, their performance remains somewhat limited, particularly for real images with complex specular highlights. To this end, we propose a three-stage network to address them. Specifically, given an input image, we first decompose it into the albedo, shading, and specular residue components to estimate a coarse specular-free image. Then, we further refine the coarse result to alleviate its visual artifacts such as color distortion. Finally, we adjust the tone of the refined result to match that of the input as closely as possible. In addition, to facilitate network training and quantitative evaluation, we present a large-scale synthetic dataset of object-level images, covering diverse objects and illumination conditions. Extensive experiments illustrate that our network is able to generalize well to unseen real object-level images, and even produce good results for scene-level images with multiple background objects and complex lighting.
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)
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)
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)
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)
Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline
School of Aeronautics and Astronautics, Zhejiang University(浙江大学航空航天学院);Huanjiang Laboratory(浣江实验室);Hangzhou Institute of Technology, Xidian University(西安电子科技大学杭州研究院);The Chinese University of Hong Kong(香港中文大学)
SARU: A Shadow-Aware and Removal Unified Framework for Remote Sensing Images with New Benchmarks
MOE Key Lab of ICSP, Anhui Provincial Key Lab of Multimodal Cognitive Computation, IMIS Lab of Anhui Province, School of Computer Science and Technology, Anhui University, Hefei, China(教育部信息与通信系统重点实验室、安徽省多模态认知计算重点实验室、安徽省IMIS实验室、计算机科学与技术学院、安徽大学、合肥,中国);Graduate School of Frontier Sciences, The University of Tokyo, Chiba, 277-8561, Japan(前沿科学研究生院、东京大学、千叶,日本)
Dim the Lights! -- Low-Rank Prior Temporal Data for Specular-Free Video Recovery
George Washington University(乔治华盛顿大学);Taibah University(泰巴大学);University of Cambridge(剑桥大学);Université Clermont Auvergne(克莱蒙奥弗涅大学);CNRS(法国国家科学研究中心);SIGMA Clermont(克莱蒙西格玛工程师学院);Institut Pascal(帕斯卡研究所)
FASR-Net: Unsupervised Shadow Removal Leveraging Inherent Frequency Priors
Faculty of Information Engineering and Automation, Kunming University of Science and Technology(昆明理工大学信息工程与自动化学院);College of Mechatronics and Control Engineering, Shenzhen University(深圳大学机电与控制工程学院)
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)
SR3D: Unleashing Single-view 3D Reconstruction for Transparent and Specular Object Grasping
Beijing University of Posts and Telecommunications(北京邮电大学);Center on Frontiers of Computing Studies, Peking University(北京大学前沿计算研究中心);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)
AlbedoEdit: Unified Instance-Level Video Editing with Albedo Guidance
Max Planck Institute for Informatics(马克斯·普朗克信息研究所);University of California Santa Barbara(加州大学圣巴巴拉分校);NVIDIA Research(NVIDIA研究);Texas A & M University(德克萨斯A&M大学)
GRRE: Leveraging G-Channel Removed Reconstruction Error for Robust Detection of AI-Generated Images
College of Cyber Science and Technology, Hunan University(湖南大学网络安全科学学院);Department of Computer Science, State University of New York at New Paltz(纽约州立大学新帕尔兹分校计算机科学系)
Removal then Selection: A Coarse-to-Fine Fusion Perspective for RGB-Infrared Object Detection
Institute of Artificial Intelligence, Hangzhou Innovation Institute, Beihang University, Beijing(北京航空航天大学人工智能研究院,杭州创新院);Institute of Artificial Intelligence, Beihang University(北京航空航天大学人工智能研究院);School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院);Beijing Institute of Control and Electronic Technology(北京控制与电子技术研究所)