* add comparisons for animevideo-v3 model * fix markdown table format Co-authored-by: yanzewu <yanzewu@tencent.com>
7.3 KiB
7.3 KiB
Comparisons among different anime models
Update News
- 2022/04/22: Release AnimeVideo-v3, we have made the following improvements:
- better naturalness
- less artifacts
- more faithful to the original colors
- better texture restoration
- better background restoration
Compare methods
- waifu2x: the hyperparameters:
tile=0,noiselevel=2 - Real-CUGAN:
we use the 20220227 version,
the hyperparameters are:
cache_mode=0,tile=0,alpha=1. - RealESRGAN-AnimeVideo-v3 (ours latest released animevideo model)
results
You may need to zoom in for comparing details, or click the image to see in the full size.
| Input | waifu2x | Real-CUGAN | RealESRGAN AnimeVideo-v3 |
|---|---|---|---|
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
Speed
pytorch
Note that we only report the model speed, and IO time is not considered.
| GPU | Input Resolution | waifu2x | Real-CUGAN | RealESRGAN-AnimeVideo-v3 |
|---|---|---|---|---|
| V100 | 1921x1080 | - | 3.4 fps | 10.0 fps |
| V100 | 1280x720 | - | 7.2 fps | 22.6 fps |
| V100 | 640x480 | - | 24.4 fps | 65.9 fps |
ncnn
- update ncnn library of Real-ESRGAN-ncnn-vulkan for a fair comparison.



















































