APISR: Anime Production Inspired Real-World Anime Super-Resolution
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913299169280000 |
|---|---|
| author | Wang, Boyang Yang, Fengyu Yu, Xihang Zhang, Chao Zhao, Hanbin |
| author_facet | Wang, Boyang Yang, Fengyu Yu, Xihang Zhang, Chao Zhao, Hanbin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_01598 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | APISR: Anime Production Inspired Real-World Anime Super-Resolution Wang, Boyang Yang, Fengyu Yu, Xihang Zhang, Chao Zhao, Hanbin Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition 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. |
| title | APISR: Anime Production Inspired Real-World Anime Super-Resolution |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.01598 |