PhD Research Intern, 3D World Models

Overview

SpAItial is offering PhD Research Intern positions based in Munich, Germany, focusing on generative AI, computer vision, and reality simulation. The internship lasts for a duration of 5 to 7 months, during which interns work alongside the research team to address open problems in 3D generation and reconstruction. The primary goal of the position is for the intern to own a well-defined research question and work toward publishing a scientific paper in leading conferences such as CVPR, ICCV, ECCV, SIGGRAPH, NeurIPS, and ICLR.

Requirements

Applicants must currently be enrolled in the third year or beyond of a PhD program in computer science, computer vision, computer graphics, machine learning, or a related field. Candidates are required to have authored two to three first-author papers at top-tier conferences including CVPR, ICCV, ECCV, SIGGRAPH, NeurIPS, or ICLR. Additionally, candidates must possess strong knowledge in at least one core area, which includes generative video and diffusion models, scene representations such as Gaussian splats and radiance fields, or 3D reconstruction ranging from per-scene optimization to feed-forward models.

What you get

Interns will have the opportunity to explore novel research directions in 3D generation, reconstruction, and world models while collaborating closely with the research team. Participants will design, implement, and evaluate state-of-the-art methods to convert innovative research ideas into functional systems and prototypes. Furthermore, interns will present their findings and contribute to scientific publications targeting premier conferences in the fields of computer vision, computer graphics, and machine learning.