对于输入帧的处理
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1k
- Forks
- 131
- PR merge metrics
- No merged PRs in 30d
Description
作者您好，在RIFE的inference_img.py中，是这样处理输入帧：
https://github.com/hzwer/ECCV2022-RIFE/blob/638322e8bfe6daca4439f7b56503fef4b090d34f/inference_img.py#L57-L60
在Practical-RIFE中，输入帧被resize到(448, 256)：
https://github.com/hzwer/Practical-RIFE/blob/82906f05c31d32d8e84075e3ab63b1f6f9cd57ba/inference_img.py#L53-L58
请问这两种处理方式会对结果造成影响吗？为什么处理方式不一样？
另外还想请教一些问题：
- 如果测试集是Xiph,分辨率都是(4096, 2160)，但我在测试的时候先把视频帧resize到(256,448)，得到光流后，把光流插值到(4096, 2160)，最后的插帧结果也是(4096, 2160)，这样可以叫做4K视频插帧吗？还是必须保证输入大小是(4096, 2160)？
- 如果对输入帧进行resize，得到插帧结果后，再通过插值恢复原始大小，可以通过这种方式实现高分辨率视频插帧吗？
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Read the linked inference_img.py sections in ECCV2022-RIFE and Practical-RIFE first, then compare their input resizing and optical-flow interpolation steps. Check the Xiph dataset dimensions and the referenced evaluation path. Done means documenting whether each resizing workflow changes the interpolation result and what input-size requirements apply.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100