3D Computer Vision

New 3D Computer Vision Lectures

Written on 25.07.2023 08:33 by Eddy Ilg

The CVMP lab will offer the new lectures “3D Computer Vision” and “3D Real World Modeling and Inference” in upcoming winter and summer semesters.

The 3D Computer Vision lecture will teach you the fundamentals of going from 2D images to 3D. After having given an intuition of the field and traditional methods, it will proceed to state-of-the-art approaches and provide you with a basis for working in 3D vision. The lecture will cover the mathematical fundamentals, feature matching, stereo, optical flow and scene flow estimation, rigid 3D reconstruction, non-rigid 3D reconstruction and SLAM. 

The 3D Real World Modeling and Inference lecture will teach you how to design models in 3D. It will start with introducing the basic 3D representations ranging from point clouds to meshes, triplanes and voxel grids. Basic and modern deep learning techniques to train and perform inference on these representations will be introduced. Afterwards, the recent implicit representations such as NeRF and DeepSDF with MLPs and how to encode 3D scenes with them efficiently will be covered. Many modern models involve generative models and subsequently the basics of generative models from autodecoders to GANs and finally diffusion models will be presented.