[ECCV 2022] MuLUT: Cooperating Mulitple Look-Up Tables for Efficient Image Super-Resolution

[T-PAMI 2024] Toward DNN of LUTs: Learning Efficient Image Restoration with Multiple Look-Up Tables

Jiacheng Li, Chang Chen, Zhen Cheng, and Zhiwei Xiong

ECCV Paper | ECCV Paper Supp. | T-PAMI Paper | Poster | Project Page | Intro Video | Code

Introduction

This repository contains the Android implementation of MuLUT (as well as SRLUT and interpolation methods) for efficient image super-resolution. As we explained in the manuscript, it is implemented with the standard JAVA API of IntStream.parrallel(). There is a great room to be further optimized for mobile devices. We welcome contributions from the community to improve this implementation.

The APK file can be downloaded from Release. Try it out!

Citation

If you find our work helpful, please cite the following papers.

@InProceedings{Li_2022_MuLUT,
      author    = {Li, Jiacheng and Chen, Chang and Cheng, Zhen and Xiong, Zhiwei},
      title     = {{MuLUT}: Cooperating Multiple Look-Up Tables for Efficient Image Super-Resolution},
      booktitle = {ECCV},
      year      = {2022},
  }
  
@ARTICLE{10530442,
      author    = {Li, Jiacheng and Chen, Chang and Cheng, Zhen and Xiong, Zhiwei},
      title     = {Toward {DNN} of {LUTs}: Learning Efficient Image Restoration with Multiple Look-Up Tables},
      journal   = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
      year      = {2024},
      volume    = {},
      number    = {},
      pages     = {1-18},
      doi       = {10.1109/TPAMI.2024.3401048}
  }
  

@InProceedings{Li_2023_LeRF,
      author    = {Li, Jiacheng and Chen, Chang and Huang, Wei and Lang, Zhiqiang and Song, Fenglong and Yan, Youliang and Xiong, Zhiwei},
      title     = {Learning Steerable Function for Efficient Image Resampling},
      booktitle = {CVPR},
      year      = {2023},
  }

License

MIT