March 8, 2024, 5:42 a.m. | Brian B. Moser, Stanislav Frolov, Federico Raue, Sebastian Palacio, Andreas Dengel

cs.LG updates on arXiv.org arxiv.org

arXiv:2307.04593v1 Announce Type: cross
Abstract: This work introduces Differential Wavelet Amplifier (DWA), a drop-in module for wavelet-based image Super-Resolution (SR). DWA invigorates an approach recently receiving less attention, namely Discrete Wavelet Transformation (DWT). DWT enables an efficient image representation for SR and reduces the spatial area of its input by a factor of 4, the overall model size, and computation cost, framing it as an attractive approach for sustainable ML. Our proposed DWA model improves wavelet-based SR models by leveraging …

abstract arxiv attention cs.ai cs.cv cs.lg differential eess.iv image representation spatial transformation type wavelet work

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US