Perceiving the similarity between images has been a long-standing and fundamental problem underlying various visual generation tasks. Predominant approaches measure the inter-image distance by computing pointwise absolute deviations, which tends to estimate the median of instance distributions and leads to blurs and artifacts in the generated images. This paper presents MoNCE, a versatile metric that introduces image contrast to learn a calibrated metric for the perception of multifaceted inter-image distances. Unlike vanilla contrast which indiscriminately pushes negative samples from the anchor regardless of their similarity, we propose to re-weight the pushing force of negative samples adaptively according to their similarity to the anchor, which facilitates the contrastive learning from informative negative samples. Since multiple patch-level contrastive objectives are involved in image distance measurement, we introduce optimal transport in MoNCE to modulate the pushing force of negative samples collaboratively across multiple contrastive objectives. Extensive experiments over multiple image translation tasks show that the proposed MoNCE outperforms various prevailing metrics substantially. The code is available at https://github.com/fnzhan/MoNCE.
SpiS-GAN: Spiral-Modulated Handwriting Synthesis with Star Operation
University of Information Technology（信息技术大学）；Vietnam National University（越南国立大学）；AJ Technologies（AJ科技公司）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）
FREAK: Frequency-modulated High-fidelity and Real-time Audio-driven Talking Portrait Synthesis
School of Computer Science and Engineering, Southeast University（计算机科学与工程学院，东南大学）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Ministry of Education, China（新一代人工智能技术及其交叉应用重点实验室，教育部，中国）
GH-Feat: Learning Versatile Generative Hierarchical Features from GANs
The Chinese University of Hong Kong（香港中文大学）；Ant Research（蚂蚁研究院）；The Hong Kong University of Science and Technology（香港科技大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization
Mohamed bin Zayed University of Artificial Intelligence（Mohamed bin Zayed大学人工智能学院）；University of Trento（特伦托大学）；Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University（香港理工大学土木与环境工程系）；South China University of Technology（华南理工大学）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Institute of Big Data, Fudan University（复旦大学大数据研究院）；Shanghai Jiao Tong University（上海交通大学）
Noise Consistency Regularization for Improved Subject-Driven Image Synthesis
The Australian National University（澳大利亚国立大学）；Rutgers University（罗格斯大学）；Data61 CSIRO（澳大利亚联邦科学与工业研究组织 Data61）；Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室）
Precision Synthesis of Multi-Tracer PET via VLM-Modulated Rectified Flow for Stratifying Mild Cognitive Impairment
School of Mathematics and Statistics, Xi'an Jiaotong University（西安交通大学数学与统计学学院）；Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi'an Jiaotong University（教育部生物医学信息工程重点实验室，西安交通大学生命科学与技术学院）；Department of Radiology and Nuclear Medicine, Xuanwu Hospital, Capital Medical University（首都医科大学宣武医院放射科与核医学科）；Research Center for Intelligent Medical Equipment and Devices (IMED), Xi'an Jiaotong University（智能医疗设备与器件研究中心（IMED），西安交通大学）
我们开发了一个有效的点云渲染管道，用于新的视图合成，它可以实现高保真的局部细节重建，实时渲染和用户友好的编辑。在我们的管道的心脏是一个自适应频率调制模块，称为自适应频率网络（AFNet），它利用超网络来学习局部纹理频率编码，该编码连续注入自适应频率激活层以调制隐式辐射信号。该机制以较小的计算量提高了网络的频率表达能力，具有更丰富的频率基支持。为了进一步提高性能，还提出了一个预处理模块，通过点不透明度估计点云几何优化。与隐式渲染相比，我们的管道支持基于点云操作的高保真交互式编辑。在NeRF-Synthetic，ScanNet，DTU和Tanks and Temples数据集上的大量实验结果表明，与最先进的方法相比，我们的方法在PSNR，SSIM和LPIPS方面取得了优异的性能。
