Roberto Henschel

4

Papers

154

Total Citations

Papers (4)

StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text

LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking

Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths

Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators