Search papers, labs, and topics across Lattice.
3
0
5
3
A new large-scale dataset of human-annotated video crops enables training models that adapt videos to different aspect ratios while preserving visual quality and meaning.
Control video super-resolution with a few keyframes: SparkVSR lets you guide the process and fix artifacts, unlike black-box VSR models.
The YT-NTU-AVQ dataset, 10x larger than previous AVQA datasets, unlocks new possibilities for training and evaluating multimodal perception models by offering unprecedented scale and diversity.
