Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/justin62628/squirrel-rife
效果更好的补帧软件,显存占用更小,是DAIN速度的10-25倍,包含抽帧处理,去除动漫卡顿感
https://github.com/justin62628/squirrel-rife
animation interpolation rife slomo smooth video videoframeinterpolation
Last synced: 30 days ago
JSON representation
效果更好的补帧软件,显存占用更小,是DAIN速度的10-25倍,包含抽帧处理,去除动漫卡顿感
- Host: GitHub
- URL: https://github.com/justin62628/squirrel-rife
- Owner: Justin62628
- License: gpl-3.0
- Created: 2021-01-31T07:44:07.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2023-05-28T13:01:43.000Z (over 1 year ago)
- Last Synced: 2024-10-15T05:23:53.730Z (30 days ago)
- Topics: animation, interpolation, rife, slomo, smooth, video, videoframeinterpolation
- Language: Python
- Homepage:
- Size: 5.47 MB
- Stars: 3,086
- Watchers: 16
- Forks: 176
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Squirrel-RIFE
- 基于RIFE算法的中文补帧软件----
## ✨ 特点 Feature
- 效果更好,显存占用极小,是DAIN速度的二十倍
- More efficient, less memory used, and 20 times faster than DAIN
- 高精度转场识别,可在多数视频中达到95%以上的精确度,不破坏丝滑效果
- Ultra high precision of transition recognition, reaching 95%+ accuracy in most videos without affecting smoothness
- 包含抽帧处理,可去除动漫卡顿感
- Deduplication removes animation clipping## 🖥 系统要求 System Requirements
- Windows 10 及以上操作系统
- Windows 10 or above- NVIDIA 显卡需要 GeForce Experience 所安装的驱动版本大于等于460.89
- NVIDIA GPU(driver > 460.89)- 2GB 以上显存, 4GB 左右的空余运行内存以及4GB+的磁盘剩余空间
- 2GB+ of video card memory, 4GB+ of DDR3 memory and 4GB+ of free disk space## 🤝 参考 Reference & Acknowledgement
- Video Frame Interpolation Algorithm: [RIFE](https://github.com/hzwer/arXiv2020-RIFE)
- NCNN Support: [RIFE-NCNN](https://github.com/nihui/rife-ncnn-vulkan)
- SWIG Wraps: [Everything-ncnn-vulkan-python](https://github.com/orgs/media2x/repositories)
- UI Design: [QCandyUi](https://github.com/shuoGG1239/QCandyUi)
- Steamworks Interface: [SteamworksPy](https://github.com/philippj/SteamworksPy)
- Encode Supports: [FFmpeg](https://github.com/FFmpeg/FFmpeg), [QSVEnc](https://github.com/rigaya/QSVEnc), [NVEnc](https://github.com/rigaya/NVEnc), [dovi_tool](https://github.com/quietvoid/dovi_tool), [dlb_mp4base](https://github.com/DolbyLaboratories/dlb_mp4base), [hdr10plus_parser](https://github.com/quietvoid/hdr10plus_parser)
- Super Resolution Algorithm: [waifu2x](https://github.com/nagadomi/waifu2x), [RealESR](https://github.com/xinntao/Real-ESRGAN), [RealCUGAN](https://github.com/bilibili/ailab/blob/main/Real-CUGAN/LICENSE)
- View More at `LICENSE` and `LICENSES_BUNDLE` FILE