Michael Bernasconi — accepted AI-conference papers

2025

LDIP: Long Distance Information Propagation for Video Super-Resolution

Michael Bernasconi, Abdelaziz Djelouah, Yang Zhang, Markus Gross, Christopher Schroers

ICCV 2025poster

Video super-resolution (VSR) methods typically exploit information across multiple frames to achieve high quality upscaling, with recent approaches demonstrating impressive performance. Nevertheless, challenges remain, particularly in effectively leveraging information over long distances. To addres…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Kernel Aware Resampler

Michael Bernasconi, Abdelaziz Djelouah, Farnood Salehi, Markus Gross, Christopher Schroers

CVPR 2023poster

Deep learning based methods for super-resolution have become state-of-the-art and outperform traditional approaches by a significant margin. From the initial models designed for fixed integer scaling factors (e.g. x2 or x4), efforts were made to explore different directions such as modeling blur ker…

Cited by 3 Source ↗PDF ↗Scholar ↗