3D video avatars can empower virtual communications by providing compression, privacy, entertainment, and a sense of presence in AR/VR. Best 3D photo-realistic AR/VR avatars driven by video, that can minimize uncanny effects, rely on person-specific models. However, existing person-specific photo-realistic 3D models are not robust to lighting, hence their results typically miss subtle facial behaviors and cause artifacts in the avatar. This is a major drawback for the scalability of these models in communication systems (e.g., Messenger, Skype, FaceTime) and AR/VR. This paper addresses previous limitations by learning a deep learning lighting model, that in combination with a high-quality 3D face tracking algorithm, provides a method for subtle and robust facial motion transfer from a regular video to a 3D photo-realistic avatar. Extensive experimental validation and comparisons to other state-of-the-art methods demonstrate the effectiveness of the proposed framework in real-world scenarios with variability in pose, expression, and illumination. Please visit https://www.youtube.com/watch?v=dtz1LgZR8cc for more results. Our project page can be found at https://www.cs.rochester.edu/u/lchen63.
HG-Lane: High-Fidelity Generation of Lane Scenes under Adverse Weather and Lighting Conditions without Re-annotation
Shanghai Jiao Tong University（上海交通大学）；School of Artificial Intelligence, Henan University（河南大学人工智能学院）；University of Science and Technology of China（中国科学技术大学）；AnnLab, Institute of Semiconductors, Chinese Academy of Sciences（中国科学院半导体研究所 AnnLab）；Nanyang Technological University（南洋理工大学）
HRAvatar: High-Quality and Relightable Gaussian Head Avatar
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）；International Digital Economy Academy (IDEA) Intern（国际数字经济发展学院（IDEA）实习生）
E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras
School of Electronic and Computer Engineering, Peking University（电子与计算机工程学院，北京大学）；National University of Singapore（新加坡国立大学）；School of Future Technology, Dalian University of Technology（未来技术学院，大连理工大学）
TUMTraf EMOT: Event-Based Multi-Object Tracking Dataset and Baseline for Traffic Scenarios
School of Automation, Southeast University（东南大学自动化学院）；Chair of Robotics, Artificial Intelligence and Real-time Systems, Technical University of Munich（慕尼黑技术大学机器人与人工智能与实时系统教授职位）；Department of Computer Science and Technology, Tongji University（同济大学计算机科学与技术系）
RGM: Reconstructing High-fidelity 3D Car Assets with Relightable 3D-GS Generative Model from a Single Image
AIR, Tsinghua University（清华大学AIR）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Beijing Jiaotong University（北京交通大学）；Beijing Institute of Technology（北京理工大学）
Good Deep Features to Track: Self-Supervised Feature Extraction and Tracking in Visual Odometry
Chair of Cyber-Physical-Systems（网络物理系统教授职位）；Institute of Automatic Control（自动控制研究所）；Faculty of Mechanical Engineering（机械工程学院）；RWTH Aachen University（亚琛工业大学）
VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generation
School of Data Science, Fudan University（复旦大学数据科学学院）；Shanghai Innovation Institute（上海创新研究院）；Zhejiang University（浙江大学）；Huawei Noah’s Ark Lab（华为诺亚实验室）；Westlake University（西湖大学）；School of Data Science and MOE Frontiers Center for Brain Science, Fudan University（复旦大学数据科学学院和脑科学前沿中心）；Fudan ISTBI–ZJNU Algorithm Centre for Brain-inspired Intelligence, Zhejiang Normal University（复旦大学-浙江师范大学脑启发智能算法中心）
Lighting-grounded Video Generation with Renderer-based Agent Reasoning
State Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University（北京大学计算机学院多媒体信息处理国家重点实验室）；National Engineering Research Center of Visual Technology, School of Computer Science, Peking University（北京大学计算机学院国家视觉技术工程研究中心）；Beijing Academy of Artificial Intelligence（北京智源人工智能研究院）；OpenBayes Information Technology Co., Ltd.（北京开贝信息技术有限公司）；School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院）
A training-free framework for high-fidelity appearance transfer via diffusion transformers
School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）；School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；School of New Media and Communication, Tianjin University（天津大学新媒体与传播学院）；JIUTIAN Research（中移九天）；State Key Laboratory of Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）
Diving into Darkness: A Dual-Modulated Framework for High-Fidelity Super-Resolution in Ultra-Dark Environments
School of Software Technology, Dalian University of Technology（大连理工大学软件学院）；School of Mathematical Science, Dalian University of Technology（大连理工大学数学科学学院）
Contrastive Context-Aware Learning for 3D High-Fidelity Mask Face Presentation Attack Detection
MUST（澳门科技大学）；Mininglamp Academy of Sciences, Mininglamp Technology（明略科技集团明略科学院）；NLPR, CASIA, UCAS（中国科学院自动化研究所模式识别国家重点实验室，中国科学院大学）；CVC, UB（巴塞罗那大学计算机视觉中心）；Baidu Research（百度研究院）；Westlake University（西湖大学）；University of Oulu（奥卢大学）
High-Fidelity 4D Hand-Object Capture via Multi-View Spatiotemporal Tracking and Physics-Aware Gaussians
Google XR（谷歌XR）；University of Science and Technology of China (USTC)（中国科学技术大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Beyond Shadows: A Large-Scale Benchmark and Multi-Stage Framework for High-Fidelity Facial Shadow Removal
New York Institute of Technology（纽约理工学院）；Shanghai University（上海大学）；Central South University（中南大学）；Xi'an Jiaotong-Liverpool University（西安交通大学利物浦大学）；Huizhou University（惠州大学）
