Page 12: Research news on Computational 3D vision

Computational 3D vision concerns algorithms and sensor systems that infer three-dimensional structure, motion, and semantics from visual and related signals. Methods span monocular and multi-view 3D reconstruction, depth estimation, inverse rendering, and 4D scene capture, often integrating LiDAR, radar, infrared, and event or neuromorphic sensors. Deep learning architectures and data-driven simulation play central roles in segmentation, pose estimation, anomaly detection, and novel view synthesis, enabling robust perception, mapping, and editing of complex environments for robotics, autonomous systems, and immersive displays.

Machine learning & AI

How artificial intelligence can learn from mice

The ability to precisely predict movements is essential not only for humans and animals, but also for many AI applications—from autonomous driving to robotics. Researchers at the Technical University of Munich (TUM) have ...

Hardware

'Optical neural engine' can solve partial differential equations

Partial differential equations (PDEs) are a class of mathematical problems that represent the interplay of multiple variables, and therefore have predictive power when it comes to complex physical systems. Solving these equations ...

page 12 from 17