Learning directly from boundary representations (B-reps) has significantly advanced 3D CAD analysis. However, state-of-the-art B-rep learning methods rely on absolute coordinates and normals to encode global context, making them highly sensitive to rotations. Our experiments reveal that models achieving over 95% accuracy on aligned benchmarks can collapse to as low as 10% under arbitrary $\mathbf{SO}(3)$ rotations. To address this, we introduce FoV-Net, the first B-rep learning framework that captures both local surface geometry and global structural context in a rotation-invariant manner. Each face is represented by a Local Reference Frame (LRF) UV-grid that encodes its local surface geometry, and by Field-of-View (FoV) grids that capture the surrounding 3D context by casting rays and recording intersections with neighboring faces. Lightweight CNNs extract per-face features, which are propagated over the B-rep graph using a graph attention network. FoV-Net achieves state-of-the-art performance on B-rep classification and segmentation benchmarks, demonstrating robustness to arbitrary rotations while also requiring less training data to achieve strong results.
UltraG-Ray: Physics-Based Gaussian Ray Casting for Novel Ultrasound View Synthesis
Chair for Computer Aided Medical Procedures (CAMP), Technical University of Munich（慕尼黑工业大学计算机辅助医疗程序教席）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）
RAGA: Real Time Ray Traced Gaussian Shadow Casting for 3DGS Avatar-Scene Interaction
Tübingen AI Center, University of Tübingen, Germany（图宾根人工智能中心，图宾根大学，德国）；Max Planck Institute for Informatics, Saarland Informatics Campus, Germany（马克斯·普朗克研究所信息学院，萨尔兰信息学院，德国）；Imperial College London, UK（伦敦帝国理工学院，英国）；King Abdullah University of Science and Technology (KAUST), Saudi Arabia（国王阿卜杜勒阿齐兹科技大学（KAUST），沙特阿拉伯）；Snap Inc., USA（Snap公司，美国）
Field-of-View Extension for Brain Diffusion MRI via Deep Generative Models
Vanderbilt University（范德堡大学）；Vanderbilt University Medical Center（范德堡大学医学中心）；University of Washington（华盛顿大学）；University of Wisconsin School of Medicine and Public Health（威斯康星大学医学院与公共卫生学院）；University of Southern California（南加州大学）
360 Panorama Synthesis from a Sparse Set of Images with Unknown Field of View
Inha University（仁荷大学）
360图像代表在所有可能的观看方向上捕获的场景，并使观看者能够在场景周围自由导航，从而提供沉浸式体验。相反，常规图像表示具有小的或有限的视场（FOV）的单个观看方向上的场景。因此，只有某些部分的场景被观察到，并有价值的信息，周围的丢失。在本文中，提出了一种基于学习的方法，该方法从稀疏的常规图像集（通常为4幅图像）重建360 x 180的场景。所提出的方法首先估计输入图像相对于全景的FOV。估计的FOV然后被用作用于合成高分辨率360全景输出的先验。所提出的方法克服了基于学习的方法在合成高分辨率图像（高达512 $\times$ 1024）的困难。实验结果表明，该方法产生的360全景具有合理的质量。结果还表明，所提出的方法优于替代方法，可以推广到非全景场景和智能手机摄像头捕获的图像。
Efficient Image-to-Image Schrödinger Bridge for CT Field of View Extension
Institute of Medical Technology, Peking University Health Science Center（北京大学人民医院医学技术研究所）；Shanghai Cancer Center, Fudan University（复旦大学上海癌症中心）；Department of Electrical and Computer Engineering, University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校电气与计算机工程系）；Beijing Key Laboratory of Intelligent Neuromodulation and Brain Disorder Treatment（北京智能神经调控与脑疾病治疗重点实验室）
OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback
Hunan University（湖南大学）；Zhejiang University（浙江大学）；Ant Group（蚂蚁集团）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；INSAIT, Sofia University ``St. Kliment Ohridski''（INSAIT，索菲亚大学『圣克莱门特·奥赫里迪斯』）
Point-Focused Attention Meets Context-Scan State Space: Robust Biological Visual Perception for Point Cloud Representation
College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics（南京航空航天大学人工智能学院）；School of Mathematical Sciences, Beijing University of Posts and Telecommunications（北京邮电大学数学科学学院）
