Role Overview
Research at the intersection of 3D, image, video, and generative AI. Join Adobe Research London to explore how unifying image, video, and 3D modalities can yield richer, more controllable generative spaces. This 3-month hybrid internship (starting from February 2027) is aimed at PhD and MS researchers, with large-scale GPU clusters, specialized datasets, and 1:1 mentorship from senior research scientists.
Responsibilities
- Bridge 3D and generative video: investigate compact 3D representations (neural fields, Gaussian Splatting, explicit geometry) alongside video diffusion/autoregressive models for precise spatial and temporal control.
- Combine generative models with classical rendering, integrating physically based rendering (PBR) into hybrid generative/agentic pipelines.
- Develop novel methods and target top-tier publications (SIGGRAPH, ACM TOG, CVPR, ICCV, NeurIPS, ICLR).
- Align research with your dissertation and build sustained collaborations beyond the internship.
Requirements
- Currently pursuing a PhD or MS in Computer Science, specializing in Computer Vision, Graphics, Machine Learning, or a closely related field; exceptional senior undergraduates with strong research output will be considered.
- Solid track record or coursework in generative modeling (diffusion / flow matching / autoregressive), computer graphics / vision, and/or 3D scene representation.
- Proficient in modern deep learning frameworks (PyTorch) with strong experimental rigor.