CompVis

AI & ML interests

Generative approaches for visual synthesis, Invertible deep models for explainable AI, Deep metric and representation learning, self-supervised learning paradigms

Recent Activity

FrankFundel  authored a paper about 8 hours ago

What Moves? Localized Motion Representations for Compositional Scene Control

FrankFundel  authored a paper about 8 hours ago

DisMo: Disentangled Motion Representations for Open-World Motion Transfer

FrankFundel  authored a paper about 8 hours ago

Distillation of Diffusion Features for Semantic Correspondence

View all activity

Papers

Improved Distributional Diffusion Models

RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video

View all Papers

Team members 37