works on
compressed face video 1cpu inference 1deep learning 1face enhancement 1face super-resolution 1few-shot learning 1image alignment 1low bitrate video 1low-compute inference 1real-time processing 1real-time video processing 1reference-based learning 1

From the 3 of 3 linked papers with an AI index.

most citedReference-Based Face Super-Resolution Using the Spatial Transformer

3 citations · 3 across the 3 of their papers we have counts for

collaborators

3 papers

cs.CV2026

FSFVE: Few Shot Compressed Face Video Enhancement

Varun Ramesh Jois, Antonella DiLillo, James Storer

The paper introduces a framework that can train a model from as few as 10 face frames to enhance highly compressed video‑call streams in real time on low‑compute devices.

cs.CV2026

RTFVE: Realtime Face Video Enhancement

Varun Ramesh Jois, Antonella DiLillo, James Storer

The paper introduces RTFVE, a real‑time face video enhancement model that can be integrated with any video decoder and runs on ordinary CPUs, improving perceptual quality of low‑bi…

cs.CV2026★ 3 cited

Reference-Based Face Super-Resolution Using the Spatial Transformer

Varun Ramesh Jois, Antonella DiLillo, James Storer

The paper introduces a reference-based face super-resolution method that leverages high‑resolution reference images and a spatial transformer alignment module to improve detail rec…