19–21 Nov 2026
"Alexandru Ioan Cuza" University of Iasi and "Gheorghe Asachi" Technical University of Iași
Europe/Bucharest timezone

High-Throughput JPEG Restoration via Mean Flows

19 Nov 2026, 17:15
15m
Room 3

Room 3

UAIC

Speaker

Mihai-Alexandru Radu (Faculty of Physics, "Alexandru Ioan Cuza" University of Iași)

Description

Recent JPEG restoration systems achieve strong visual quality with large models, but their computational cost often limits efficient on-device deployment. We present a 65M-parameter generative restorer that improves LPIPS over three regression baselines in seven of nine held-out conditions on LIVE-1, Urban100, and DIV2K validation, while sustaining 8.05 images/s at 720p on a single RTX 3090. Trained from scratch, the model replaces learned VAE encoding and decoding with an exactly invertible two-level Haar transform. A rank-enhanced linear-attention DiT predicts clean wavelet-domain residuals and internally estimates compression severity. A MeanFlow objective enables inference with one or two network evaluations without distillation. Although large pretrained priors remain stronger on several quality metrics, our approach offers a compact, high-throughput alternative for resource-constrained JPEG restoration.

Authors

Mihai-Alexandru Radu (Faculty of Physics, "Alexandru Ioan Cuza" University of Iași) Stefan-Alexandru Asandei (Independent researcher)

Presentation materials

There are no materials yet.