Search papers, labs, and topics across Lattice.
Eindhoven University of Technology
3
0
5
13
Ditch the computational bloat: DeltaWorld slashes parameters by 35x and FLOPs by 2000x while generating more realistic video futures.
Get 3x faster image segmentation and comparable video segmentation performance to fine-tuned models, all while keeping your vision encoder frozen.
Ditch the complex trackers: a plain ViT encoder, augmented with a clever query propagation trick, delivers state-of-the-art video segmentation at 10x the speed.
