|
--- |
|
license: gpl-3.0 |
|
--- |
|
|
|
# APISR Model Card |
|
|
|
<div align="center"> |
|
|
|
[**Paper (ArXiv)**](https://arxiv.org/pdf/2403.01598.pdf) **|** [**Code**](https://github.com/Kiteretsu77/APISR) **|** [🤗 **Gradio demo**](https://huggingface.co/spaces/HikariDawn/APISR) |
|
|
|
</div> |
|
|
|
## Introduction |
|
While real-world anime super-resolution (SR) has gained increasing attention in the SR community, existing methods still adopt techniques from the photorealistic |
|
domain. In this paper, we analyze the anime production workflow and rethink how to use characteristics of it for the sake of the real-world anime SR. First, we argue that |
|
video networks and datasets are not necessary for anime |
|
SR due to the repetition use of hand-drawing frames. Instead, we propose an anime image collection pipeline by |
|
choosing the least compressed and the most informative |
|
frames from the video sources. Based on this pipeline, |
|
we introduce the Anime Production-oriented Image (API) |
|
dataset. In addition, we identify two anime-specific challenges of distorted and faint hand-drawn lines and unwanted color artifacts. We address the first issue by introducing a prediction-oriented compression module in the |
|
image degradation model and a pseudo-ground truth preparation with enhanced hand-drawn lines. In addition, we introduce the balanced twin perceptual loss combining both |
|
anime and photorealistic high-level features to mitigate unwanted color artifacts and increase visual clarity. We evaluate our method through extensive experiments on the public |
|
benchmark, showing our method outperforms state-of-the-art anime dataset-trained approaches. |
|
|
|
  |
|
|
|
## WorkFlow |
|
<div align="center"> |
|
<img src="https://raw.githubusercontent.com/Kiteretsu77/APISR/main/__assets__/workflow.png", width="100%", height="100%", style="float: left"> |
|
</div> |
|
|
|
  |
|
|
|
## Visual Results |
|
|
|
[<img src="https://raw.githubusercontent.com/Kiteretsu77/APISR/main/__assets__/visual_results/0079_visual.png" height="223px"/>](https://imgsli.com/MjQ1NzIz) [<img src="https://raw.githubusercontent.com/Kiteretsu77/APISR/main/__assets__/visual_results/0079_2_visual.png" height="223px"/>](https://imgsli.com/MjQ1NzMw) |
|
|
|
[<img src="https://raw.githubusercontent.com/Kiteretsu77/APISR/main/__assets__/visual_results/pokemon_visual.png" height="223px"/>](https://imgsli.com/MjQ1NzIy) [<img src="https://raw.githubusercontent.com/Kiteretsu77/APISR/main/__assets__/visual_results/pokemon2_visual.png" height="223px"/>](https://imgsli.com/MjQ1NzM5) |
|
|
|
[<img src="https://raw.githubusercontent.com/Kiteretsu77/APISR/main/__assets__/visual_results/eva_visual.png" height="223px"/>](https://imgsli.com/MjQ1NzIx) [<img src="https://raw.githubusercontent.com/Kiteretsu77/APISR/main/__assets__/visual_results/kiteret_visual.png" height="223px"/>](https://imgsli.com/MjQ1NzE0) |
|
|
|
[<img src="https://raw.githubusercontent.com/Kiteretsu77/APISR/main/__assets__/visual_results/f91_visual.png" height="223px"/>](https://imgsli.com/MjQ1NzMx) [<img src="https://raw.githubusercontent.com/Kiteretsu77/APISR/main/__assets__/visual_results/wataru_visual.png" height="223px"/>](https://imgsli.com/MjQ1NzMy) |
|
|
|
<div align="center"> |
|
<img src="https://raw.githubusercontent.com/Kiteretsu77/APISR/main/__assets__/AVC_RealLQ_comparison.png", width="100%", height="100%", style="float: left"> |
|
</div> |
|
|
|
|
|
## Citation |
|
```bibtex |
|
@article{wang2024apisr, |
|
title={APISR: Anime Production Inspired Real-World Anime Super-Resolution}, |
|
author={Wang, Boyang and Yang, Fengyu and Yu, Xihang and Zhang, Chao and Zhao, Hanbin}, |
|
journal={arXiv preprint arXiv:2403.01598}, |
|
year={2024} |
|
} |
|
``` |
|
|
