The field of autonomous driving is experiencing a surge of interest in world models, which aim to predict potential future scenarios based on historical observations. In this paper, we introduce DFIT-OccWorld, an efficient 3D occupancy world model that leverages decoupled dynamic flow and image-assisted training strategy, substantially improving 4D scene forecasting performance. To simplify the training process, we discard the previous two-stage training strategy and innovatively reformulate the occupancy forecasting problem as a decoupled voxels warping process. Our model forecasts future dynamic voxels by warping existing observations using voxel flow, whereas static voxels are easily obtained through pose transformation. Moreover, our method incorporates an image-assisted training paradigm to enhance prediction reliability. Specifically, differentiable volume rendering is adopted to generate rendered depth maps through predicted future volumes, which are adopted in render-based photometric consistency. Experiments demonstrate the effectiveness of our approach, showcasing its state-of-the-art performance on the nuScenes and OpenScene benchmarks for 4D occupancy forecasting, end-to-end motion planning and point cloud forecasting. Concretely, it achieves state-of-the-art performances compared to existing 3D world models while incurring substantially lower computational costs.
SA-Occ: Satellite-Assisted 3D Occupancy Prediction in Real World
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai Jiao Tong University（上海交通大学）
InfraOcc: An Infrastructure Occupancy Benchmark with Static-to-Dynamic Reasoning
Nanyang Technological University（南洋理工大学）；Zhejiang University（浙江大学）；Beihang University（北京航空航天大学）；Beijing Institute of Technology（北京理工大学）；Yanshan University（燕山大学）；Westlake University（西湖大学）；University of Hong Kong（香港大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Real-Time Glottis Detection Framework via Spatial-decoupled Feature Learning for Nasal Transnasal Intubation
Hubei Key Laboratory of Modern Manufacturing Quality Engineering, Hubei University of Technology（湖北现代制造质量工程重点实验室，湖北工业大学）；School of Mechanical Science and Engineering, Huazhong University of Science and Technology（华中科技大学机械科学与工程学院）；Department of Electronic Engineering, The Chinese University of Hong Kong（香港中文大学电子工程系）；Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education（教育部符号计算与知识工程重点实验室）；National Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家实验室）
X-Recon: Learning-based Patient-specific High-Resolution CT Reconstruction from Orthogonal X-Ray Images
Institutes of Biomedical Sciences, Fudan University（复旦大学生物医学研究院）；School of Basic Medical Sciences, Fudan University（复旦大学基础医学院）；Zhongshan Hospital, Fudan University（复旦大学附属中山医院）；Shanghai Institute of Medical Imaging（上海医学影像研究所）；Shanghai Public Health Clinical Center, Fudan University（复旦大学附属公共卫生临床中心）；Intelligent Medicine Institute, Shanghai Medical College, Fudan University（复旦大学上海医学院智能医学研究所）；Shanghai Institute of Stem Cell Research and Clinical Translation（上海干细胞研究与临床转化研究所）
Frequency-Decomposed INR for NIR-Assisted Low-Light RGB Image Denoising
College of Computer Science (College of Software), Inner Mongolia University, Hohhot, 010021, China（内蒙古大学计算机学院（软件学院））；School of Mathematics and Statistics, Wuhan University, Wuhan, 430072, China（武汉大学数学与统计学院）；Institute of Computational Imaging, Beijing Information Science and Technology University, Beijing 102206, China（北京信息科技大学计算成像研究院）
