IEEE

Deep Scene Flow Learning: From 2D Images to 3D Point Clouds

Abstract: Scene flow describes the 3D motion in a scene. It can be modeled as a single task or as a composite of the auxiliary tasks of depth, camera motion, and optical flow estimation. Deep learning ...

C-Compass: AI-based software maps proteins and lipids within cells

A new tool developed by Helmholtz Munich and the German Center for Diabetes Research and the University of Bonn makes spatial ...

All the world's buildings available as 3D models for urban and climate research

With the GlobalBuildingAtlas, a research team at the Technical University of Munich (TUM) has created the first ...
techxplore

Unique resin allows 3D-printing method to add and subtract

Additive manufacturing, or 3D printing, is normally a one-way street. In a digital light processing (DLP) printer, a structured pattern is projected onto a layer of liquid resin, which cures and ...
IEEE

Dynamic 3D Point Cloud Sequences as 2D Videos

Abstract: Dynamic 3D point cloud sequences serve as one of the most common and practical representation modalities of dynamic real-world environments. However, their unstructured nature in both ...