Multi-Domain Image Completion for Random Missing Input Data
Stanford University（斯坦福大学）；NVIDIA（英伟达）；National Institutes of Health（美国国立卫生研究院）
Liyue Shen, Wentao Zhu, Xiaosong Wang, Lei Xing, John M. Pauly, Baris Turkbey, Stephanie Anne Harmon, Thomas Hogue Sanford, Sherif Mehralivand, Peter Choyke, Br… 展开作者
Liyue Shen, Wentao Zhu, Xiaosong Wang, Lei Xing, John M. Pauly, Baris Turkbey, Stephanie Anne Harmon, Thomas Hogue Sanford, Sherif Mehralivand, Peter Choyke, Bradford Wood, Daguang Xu
Multi-domain data are widely leveraged in vision applications taking advantage of complementary information from different modalities, e.g., brain tumor segmentation from multi-parametric magnetic resonance imaging (MRI). However, due to possible data corruption and different imaging protocols, the availability of images for each domain could vary amongst multiple data sources in practice, which makes it challenging to build a universal model with a varied set of input data. To tackle this problem, we propose a general approach to complete the random missing domain(s) data in real applications. Specifically, we develop a novel multi-domain image completion method that utilizes a generative adversarial network (GAN) with a representational disentanglement scheme to extract shared skeleton encoding and separate flesh encoding across multiple domains. We further illustrate that the learned representation in multi-domain image completion could be leveraged for high-level tasks, e.g., segmentation, by introducing a unified framework consisting of image completion and segmentation with a shared content encoder. The experiments demonstrate consistent performance improvement on three datasets for brain tumor segmentation, prostate segmentation, and facial expression image completion respectively.
LoCI-DiffCom: Longitudinal Consistency-Informed Diffusion Model for 3D Infant Brain Image Completion
School of Biomedical Engineering, ShanghaiTech University（上海科技大学生物医学工程学院）；Shanghai United Imaging Intelligence Co., Ltd（上海联影智能医疗科技有限公司）；Shanghai Clinical Research and Trail Center（上海临床研究中心）
SEGAN: semi-supervised learning approach for missing data imputation
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；School of Software Technology, Zhejiang University（浙江大学软件学院）；Binjiang Institute of Zhejiang University（浙江大学滨江研究院）；China Academy of Space Technology（中国空间技术研究院）；Beijing Life Science Academy（北京生命科学研究院）；Zhengzhou Tobacco Research Institute of China National Tobacco Corporation（中国烟草总公司郑州烟草研究院）；Purdue University（普渡大学）；COSMOPlat IoT Technology Co.,Ltd.（卡奥斯物联科技有限公司）
From Missing Pieces to Masterpieces: Image Completion with Context-Adaptive Diffusion
Department of Computer Science, University of York, UK（英国约克大学计算机科学系）；SCEE, East China Normal University, China（中国华东师范大学SCEE）；Department of Electrical Engineering, Shanghai Jiao Tong University, China（中国上海交通大学电子工程系）；School of Computing and Mathematical Sciences, University of Leicester, UK（英国莱斯特大学计算与数学科学学院）；Computer Vision Laboratory, Linkoping University, Sweden（瑞典利厄浦大学计算机视觉实验室）；College of Computing and Data Science at Nanyang Technological University, Singapore（新加坡南洋理工大学计算与数据科学学院）；Institute of Artificial Intelligence (TeleAI) of China Telecom（中国电信人工智能研究所（TeleAI））
FaceCom: Towards High-fidelity 3D Facial Shape Completion via Optimization and Inpainting Guidance
Beihang University（北京航空航天大学）；Southwest University（西南大学）；Peking University School and Hospital of Stomatology（北京大学口腔医学院）；State Key Laboratory of Virtual Reality Technology and Systems（虚拟现实技术与系统国家重点实验室）
Knowledge Bridger: Towards Training-free Missing Modality Completion
Beijing Jiaotong University（北京交通大学）；Singapore Management University（新加坡国立大学）；Southeast University（东南大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Harbin Institute of Technology（哈尔滨工业大学）；Nanjing University of Science and Technology（南京理工大学）；South China University of Technology（华南理工大学）；Xiamen Institute of Technology（厦门理工学院）
Smooth Robust Tensor Completion for Background/Foreground Separation with Missing Pixels: Novel Algorithm with Convergence Guarantee
Virginia Tech（弗吉尼亚理工大学）
本研究的目的是通过将视频采集、视频恢复、背景/前景分离结合到一个框架中来解决具有缺失像素的背景/前景分离问题。为了实现这一点，平滑鲁棒张量完成（SRTC）模型被提出来恢复数据，并将其分解为静态背景和平滑前景，分别。具体地说，静态背景建模的低秩塔克分解和平滑的前景（运动物体）建模的时空连续性，这是由总变分正则化。基于张量近似交替最小化（tensor proximate alternative minimization，tenPAM）的有效算法实现求解所提出的模型，在非常温和的条件下具有全局收敛性保证。大量的实验表明，该方法显着优于国家的最先进的方法，背景/前景分离与丢失像素。
Completion of High Order Tensor Data with Missing Entries via Tensor-train Decomposition
Saitama Institute of Technology（埼玉工业大学）；RIKEN Center for Advanced Intelligence Project (AIP)（理化学研究所先进智能项目中心（AIP））；Guangdong University of Technology（广东工业大学）
SAGCNet: Spatial-Aware Graph Completion Network for Missing Slice Imputation in Population CMR Imaging
School of Engineering, College of Engineering and Physical Sciences（工程学院，工程与物理科学学院）；University of Birmingham（伯明翰大学）；Oxford Center for Clinical Magnetic Resonance Research (OCMR)（牛津临床磁共振研究中心）；University of Oxford（牛津大学）；John Radcliffe Hospital（约翰·拉德克利夫医院）；Johns Hopkins University School of Medicine（约翰霍普金斯大学医学院）；Queen Mary University London（伦敦女王大学）；Barts Health NHS Trust（巴特勒医院 NHS 信托）
Tensor Completion via Convolutional Sparse Coding Regularization
Sun Yat-sen University（中山大学）；National Engineering Research Center of Digital Life, Sun Yat-sen University（中山大学国家数字生活工程技术研究中心）；Central China Normal University（华中师范大学）
High-dimension Tensor Completion via Gradient-based Optimization Under Tensor-train Format
Graduate School of Engineering, Saitama Institute of Technology, Japan（日本埼玉科技大学工学研究科）；Tensor Learning Unit, RIKEN Center for Advanced Intelligence Project (AIP), Japan（日本RIKEN先进人工智能项目（AIP）张量学习单元）；School of Automation, Guangdong University of Technology, China（广东技术大学自动化学院）；School of Computer Science and Technology, Hangzhou Dianzi University, China（杭州电子科技大学计算机科学与技术学院）
Position-aware Guided Point Cloud Completion with CLIP Model
North China University of Technology（北方工业大学）；Peng Cheng Laboratory（鹏城实验室）；University of Copenhagen（哥本哈根大学）；University of Washington（华盛顿大学）；Skywork AI（天工智能）；Tsinghua University（清华大学）
SDR-GAIN: A High Real-Time Occluded Pedestrian Pose Completion Method for Autonomous Driving
School of Instrument Science and Engineering, Southeast University（仪器科学与工程学院，东南大学）；School of Geospatial Engineering and Science, Sun Yat-sen University（地理信息工程与科学学院，中山大学）
