Automatic photo adjustment is to mimic the photo retouching style of professional photographers and automatically adjust photos to the learned style. There have been many attempts to model the tone and the color adjustment globally with low-level color statistics. Also, spatially varying photo adjustment methods have been studied by exploiting high-level features and semantic label maps. Those methods are semantics-aware since the color mapping is dependent on the high-level semantic context. However, their performance is limited to the pre-computed hand-crafted features and it is hard to reflect user's preference to the adjustment. In this paper, we propose a deep neural network that models the semantics-aware photo adjustment. The proposed network exploits bilinear models that are the multiplicative interaction of the color and the contexual features. As the contextual features we propose the semantic adjustment map, which discovers the inherent photo retouching presets that are applied according to the scene context. The proposed method is trained using a robust loss with a scene parsing task. The experimental results show that the proposed method outperforms the existing method both quantitatively and qualitatively. The proposed method also provides users a way to retouch the photo by their own likings by giving customized adjustment maps.
Gradient-Aware Logit Adjustment Loss for Long-tailed Classifier
Anhui University(安徽大学);Hefei University of Technology(合肥工业大学);Pennsylvania State University(宾夕法尼亚州立大学);University of Science and Technology of China(中国科学技术大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合性国家科学中心人工智能研究院)
MomentBA: Second-order Spatial Moments for Anisotropic Correspondence Uncertainty in Differentiable Bundle Adjustment
Wuhan University(武汉大学);Hubei Technology Innovation Center for Spatiotemporal Information and Positioning Navigation(湖北时空信息与定位导航技术创新中心);Hubei Luojia Laboratory(湖北珞珈实验室)
Automatic Photo Adjustment Using Deep Neural Networks
University of Illinois at Urbana Champaign(伊利诺伊大学厄巴纳-香槟分校);Carnegie Mellon University(卡内基梅隆大学);Microsoft Research(微软研究院);Adobe Research(奥多比研究院);The University of Hong Kong(香港大学)
Good Graph to Optimize: Cost-Effective, Budget-Aware Bundle Adjustment in Visual SLAM
Facebook Reality Lab(Facebook现实实验室);School of Electrical and Computer Engineering, Georgia Institute of Technology(佐治亚理工学院电气与计算机工程学院);Institute of Robotics and Intelligent Machines, Georgia Institute of Technology(佐治亚理工学院机器人与智能机器研究所)
Class Confidence Aware Reweighting for Long Tailed Learning
Department of Computer Science & Engineering, Electronics & Communication Engineering, Indian Institute of Information Technology Nagpur(计算机科学与工程系、电子与通信工程系、印度信息技术学院纳格浦)
Spatial AI & Robotics (SAIR) Lab, University at Buffalo(空间人工智能与机器人实验室,布法罗大学);Georgia Institute of Technology(佐治亚理工学院);Purdue University(普渡大学);Carnegie Mellon University(卡内基梅隆大学)
Mimicking the In-Camera Color Pipeline for Camera-Aware Object Compositing
University of Toronto(多伦多大学);Vector Institute(向量研究所);University of Science and Technology of China(中国科学技术大学);Microsoft Research(微软研究院);Peking University(北京大学);NVIDIA(英伟达)
Towards Context-aware Support for Color Vision Deficiency: An Approach Integrating LLM and AR
School of Computing, Tokyo Institute of Technology(东京工业大学计算学院);International Research Center for Neurointelligence, the University of Tokyo(东京大学国际神经智能研究中心);Department of Computer Science and Engineering, Waseda University(早稻田大学计算机科学与工程学院);Center of Mathematical and Data Sciences, Kobe University(神户大学数学与数据科学中心)