ML Anthology

Efficient Super-Resolution Using MobileNetV3

Haicheng Wang, Vineeth Bhaskara, Alex Levinshtein, Stavros Tsogkas, Allan D. Jepson
ECCVW 2020 pp. 87-102
doi:10.1007/978-3-030-67070-2_5 /eccvw/2020/wang2020eccvw-efficient/

Abstract

Deep learning methods for super-resolution (SR) have been dominating in terms of performance in recent years. Such methods can potentially improve the digital zoom capabilities of most modern mobile phones, but are not directly applicable on device, due to hardware constraints. In this work, we adapt MobileNetV3 blocks, shown to work well for classification, detection and segmentation, to the task of super-resolution. The proposed models with the modified MobileNetV3 block are shown to be efficient enough to run on modern mobile phones with an accuracy approaching that of the much heavier, state-of-the-art (SOTA) super-resolution approaches.

PDF ECCVW Semantic Scholar

Cite

Text

Wang et al. "Efficient Super-Resolution Using MobileNetV3." European Conference on Computer Vision Workshops, 2020. doi:10.1007/978-3-030-67070-2_5

Markdown

[Wang et al. "Efficient Super-Resolution Using MobileNetV3." European Conference on Computer Vision Workshops, 2020.](https://mlanthology.org/eccvw/2020/wang2020eccvw-efficient/) doi:10.1007/978-3-030-67070-2_5

BibTeX

@inproceedings{wang2020eccvw-efficient,
  title     = {{Efficient Super-Resolution Using MobileNetV3}},
  author    = {Wang, Haicheng and Bhaskara, Vineeth and Levinshtein, Alex and Tsogkas, Stavros and Jepson, Allan D.},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2020},
  pages     = {87-102},
  doi       = {10.1007/978-3-030-67070-2_5},
  url       = {https://mlanthology.org/eccvw/2020/wang2020eccvw-efficient/}
}