We propose a simple yet effective reflection-free cue for robust reflection removal from a pair of flash and ambient (no-flash) images. The reflection-free cue exploits a flash-only image obtained by subtracting the ambient image from the corresponding flash image in raw data space. The flash-only image is equivalent to an image taken in a dark environment with only a flash on. We observe that this flash-only image is visually reflection-free, and thus it can provide robust cues to infer the reflection in the ambient image. Since the flash-only image usually has artifacts, we further propose a dedicated model that not only utilizes the reflection-free cue but also avoids introducing artifacts, which helps accurately estimate reflection and transmission. Our experiments on real-world images with various types of reflection demonstrate the effectiveness of our model with reflection-free flash-only cues: our model outperforms state-of-the-art reflection removal approaches by more than 5.23dB in PSNR, 0.04 in SSIM, and 0.068 in LPIPS. Our source code and dataset are publicly available at {github.com/ChenyangLEI/flash-reflection-removal}.
Glass Surface Detection: Leveraging Reflection Dynamics in Flash/No-flash Imagery
School of Artificial Intelligence and Computer Science at Jiangnan University（江南大学人工智能与计算机科学学院）；School of Information Science and Technology, University of Science and Technology of China（中国科学技术大学信息科学与技术学院）；Department of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（马尔代夫比赞大学人工智能学院计算机视觉系）；Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）
Freq-DP Net: A Dual-Branch Network for Fence Removal using Dual-Pixel and Fourier Priors
Visual Intelligence Team, Samsung Research India Bangalore（三星印度研究部视觉智能团队）；Department of Electrical Engineering, Indian Institute of Science（印度科学研究院电子工程系）
The Chinese University of Hong Kong（香港中文大学）；Shanghai AI Laboratory（上海人工智能实验室）；University of Science and Technology of China（中国科学技术大学）；Institute of Science Tokyo（东京科学大学）
FreeShadow: Training-Free Shadow Removal via Illumination Transfer and Selective Content Preservation in Diffusion Models
School of Computer Science and Engineering, South China University of Technology（华南理工大学计算机科学与工程学院）；Pazhou Lab（琶洲实验室）；Polytech Nantes, Université de Nantes（南特大学南特理工学院）
GRAR: Glass-induced Reflection Artifact Removal in LiDAR Point Clouds
College of Computer Science and Electronic Engineering, Hunan University（湖南大学计算机科学与电子工程学院）；School of Design, Hunan University（湖南大学设计学院）；School of Finance and Statistics, Hunan University（湖南大学金融与统计学院）
The Hong Kong Polytechnic University（香港理工大学）；ETH Zurich（苏黎世联邦理工学院）；Center for Artificial Intelligence and Robotics, HKISI-CAS（中国科学院香港智能科学研究所人工智能与机器人中心）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Australian National University（澳大利亚国立大学）；Data61 CSIRO, Australia（澳大利亚联邦科学与工业研究组织数据61部(CSIRO Data61)，澳大利亚(注：Data61是CSIRO的下属研究机构，按要求提取到公司/研究院级别，此处CSIRO为公司/研究院级别机构，Data61为其下属研究机构，故整体保留为Data61 CSIRO, Australia)）
Hierarchical Semantic-Visual Fusion of Visible and Near-infrared Images for Long-range Haze Removal
National Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（多光谱信息智能处理技术国家实验室，人工智能与自动化学院，华中科技大学）；State Key Laboratory of Dynamic Optical Imaging and Measurement（动态光学成像与测量国家重点实验室）
Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Era
School of Future Technology, South China University of Technology（华南理工大学未来技术学院）；Department of Computer Science and Engineering, The Chinese University of Hong Kong（香港中文大学计算机科学与工程学院）；Adobe Research（Adobe研究）
Task-Guided Prompting for Unified Remote Sensing Image Restoration
School of Electronic and Information Engineering, Ningbo University of Technology（宁波工程学院电子与信息工程学院）；University of Exeter（埃克塞特大学）；Engineering Research Center of Intelligent Finance, Ministry of Education（教育部智能金融工程研究中心）；School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics（西南财经大学计算机与人工智能学院）
