Deep Learning for Visual Computing (Computer Vision, Machine Learning, Graphics)

The internship will be in visual computing and machine learning (computer vision, machine learning, computer graphics). The exact topic depends on the student's interest, background, and current research topics in the group. To give some examples of past projects: generative models for synthesizing images, videos, textures, point clouds, or 3D geometry; generative models for image and video editing, animation, and world generation; generative models for structured content, e.g. buildings, floor plans, and street graphs; depth estimation from one or multiple images; primitive fitting; segmentation; 3D reconstruction using NerF and Gaussian splitting; vision and language for 3D content analysis and generation, e.g. segmentation, keypoint detection, editing, and modeling.

There are no pre-determined deliverables. The goal is to learn more about the research process and to work towards a high-quality publication. Students will be involved in reading literature, discussing ideas, and implementation.