Dealing with the inconsistency between a foreground object and a background image is a challenging task in high-fidelity image composition. State-of-the-art methods strive to harmonize the composed image by adapting the style of foreground objects to be compatible with the background image, whereas the potential shadow of foreground objects within the composed image which is critical to the composition realism is largely neglected. In this paper, we propose an Adversarial Image Composition Net (AIC-Net) that achieves realistic image composition by considering potential shadows that the foreground object projects in the composed image. A novel branched generation mechanism is proposed, which disentangles the generation of shadows and the transfer of foreground styles for optimal accomplishment of the two tasks simultaneously. A differentiable spatial transformation module is designed which bridges the local harmonization and the global harmonization to achieve their joint optimization effectively. Extensive experiments on pedestrian and car composition tasks show that the proposed AIC-Net achieves superior composition performance qualitatively and quantitatively.
Sparse Illumination Learning and Transfer for Single-Sample Face Recognition with Image Corruption and Misalignment
University of Science and Technology of China（中国科学技术大学）；Advanced Digital Sciences Center（先进数字科学中心）；University of California, Berkeley（加州大学伯克利分校）；ShanghaiTech University（上海科技大学）
MoCTEFuse: Illumination-Gated Mixture of Chiral Transformer Experts for Multi-Level Infrared and Visible Image Fusion
School of Optics and Photonics, Beijing Institute of Technology（光学与光电学院，北京理工大学）；School of Computer Science and Technology, Beijing Institute of Technology（计算机科学与技术学院，北京理工大学）
Text as Illumination: Spatial Contrastive Retinex Learning for Language-guided Medical Image Segmentation
School of Software Technology & DUT-RU International School of Information Science and Engineering, Dalian University of Technology（大连理工大学软件学院 & 大连理工大学-俄罗斯国际信息科学与工程学院）；School of Future Technology, Dalian University of Technology（大连理工大学未来技术学院）；Central Hospital of Dalian University of Technology（大连理工大学中心医院）；Cancer Hospital of Dalian University of Technology（大连理工大学肿瘤医院）；College of Computer Science and Engineering, Shandong University of Science and Technology（山东科技大学计算机科学与工程学院）
Learning Compositional Visual Concepts with Mutual Consistency
School of Electrical and Computer Engineering, Cornell University（康奈尔大学电气与计算机工程学院）；Siemens Corporate Technology（西门子公司技术部）；Nancy E. and Peter C. Meinig School of Biomedical Engineering, Cornell University（康奈尔大学南希·E·和彼得·C·迈尼格生物医学工程学院）
Rethinking Theoretical Illumination for Efficient Low-Light Image Enhancement
Department of Electronic Engineering, Chung Yuan Christian University（Chung Yuan Christian University电子工程系）；Department of Electrical Engineering, University of Wisconsin–Milwaukee（University of Wisconsin–Milwaukee电气工程系）；Institute of Computer Science and Engineering, National Yang Ming Chiao Tung University（National Yang Ming Chiao Tung University计算机科学与工程研究所）
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Tensor Vision Technologies（张量视觉技术公司）
视觉对象是由一个递归层次的知觉整体和部分，其属性，如形状，反射率和颜色，构成了一个层次的内在因果因素的对象外观。然而，物体外观是物体的内在和外在因果因素的组成结果，其中外在因果因素与照明和成像条件有关。因此，本文提出了一个统一的张量模型的整体和部分，并介绍了一个组成层次张量分解，解开层次因果结构的对象图像形成，并纳入多线性块张量分解作为一个特殊情况。所得到的对象表示是整体和部分表示的可解释的组合选择，其使得对象识别对遮挡鲁棒并且减少训练数据要求。我们通过在一个极其简化的合成图像数据集上进行训练，在人脸识别的背景下演示了我们的方法，并在两个数据集上报告了人脸验证结果-Freiburg数据集和由真实世界图像组成的Labeled Face in the Wild（LFW）数据集，从而证实了我们的方法适用于数据匮乏的领域。
ORCA: Hunting Compositional Failures in Text-to-Image Diffusion
Wellcome Sanger Institute（威康桑格研究所）；Cambridge Stem Cell Institute, University of Cambridge（剑桥大学剑桥干细胞研究所）；Cambridge Centre for AI in Medicine, University of Cambridge（剑桥大学剑桥人工智能医学中心）；University of Oxford（牛津大学）；Apple（苹果公司）；University of Helsinki（赫尔辛基大学）；Institute for Molecular Medicine Finland (FIMM), University of Helsinki（赫尔辛基大学芬兰分子医学研究所）；School of Computing and Information Systems, University of Melbourne（墨尔本大学计算与信息系统学院）；Department of Medicine, University of Cambridge（剑桥大学医学系）
