3D scanning and motion capture is of paramount importance for content creation, man-machine as well as machine-environment interaction. In this course we will continue the topics covered by the 3D Scanning & Motion Capture as well as by the Introduction to Deep Learning lecture. In the spirit of ‘learning by doing’ the students are asked to implement state-of-the-art reconstruction methods or current research topics in the field. Specifically, we will have projects on:
- human motion capturing (e.g., Fusion4D, BodyFusion)
- real-time facial motion capturing (spare and dense approaches)
- 3D scene reconstruction (e.g., BundleFusion)
- scan refinement (e.g., ShapeFromShading)
- neural rendering of 3D content (e.g., DeepVoxel, NeuralRendering)
- scene completion (e.g., ScanComplete)
- 3D object retrieval and alignment (e.g., Scan2CAD)
- scene understanding, instance segmentation (e.g., ScanNet, 3D-SIS)
- neural scene representations (DeepSDF, OccupancyNets, NeRF,…)
Upon completion of this module, students will have acquired extensive theoretical concepts behind state-of-the art 3D reconstruction methods, in particular in the context of human motion capturing, static object scanning, scene understanding and synthesis of captured scenes. Besides the theoretical foundations, a significant aspect lies on the practical realization and implementation of such algorithms.
In the practical course students shall get familiar with state-of-the-art 3D scanning. They will be assisted by current PhD students working in this field (regular office hours). To ensure a good progress during the semester, we will have mandatory meetings (every two weeks) where the students report their current state. In the end of the course, the students are asked to give a talk about their project and results.
Introduction to Informatics I, Analysis, Linear Algebra, Computer Graphics, 3D scanning & Motion Capture, Introduction to Deep Learning, C++