Stefanos Zafeiriou

Bridging the gap between coarse atmospheric models and local PM$_{2.5}$ variations, this framework achieves a 40x super-resolution without relying on temporal data.

LAS2 redefines the balance between speed and accuracy in stereo matching, proving that efficient models can achieve state-of-the-art results without heavy computational demands.

Synthesizing realistic hand-object interactions is now possible with HO-Flow, a framework that leverages masked flow matching and interaction-aware VAEs to achieve state-of-the-art results in motion diversity and physical plausibility.

Rectified flows can generate synthetic skin lesion images that boost classification accuracy by up to 9% compared to diffusion models, offering a promising solution to data scarcity in dermatology.

MLLMs can now better understand your pointing with Hand Intent Tokens (HINT), boosting accuracy on egocentric video question answering by 6.6% on a new benchmark.