But on closer inspection, although in the presentation video it looks almost as good, the interface looks very similar to VEAI but with fewer options. For example, the preview option is missing and there is only one output format. there are not as many models depending on the type of video to improve. See the video: AVCLabs - Video Enhancer AI [ COMPLETE Review ] - YouTube
That being said, I prefer VEAI because it is more complete
I have just tested with one very short clip.
My first impression is the AVCLabs output seem sharper/crispier. It seem that AVCLabs have done some deblurring to the footage. (It make me feel like processed by Sharpen AI )
However, the output footage is not as smooth as VEAI. It seem that they treat each frame as a separate photo and enhance it one by one without consider the data of pervious/next frame.
Also the AVCLabs takes much longer time to process.
Anyway, IMO competition is always good for consumer.
I didn’t know about BSRGAN before, after some searching it seem than BSRGAN algorithm does very well on old portrait photo and they reconstruct face detail much better than many other AI software.
If only. Can’t touch the Chinese knock offs though. No point when their government is just gonna say it’s a unique piece of software and nothing was stolen.
xd. It’s pretty obvious though. The color of the interface is identical. The layout of the icons is identical. It is certainly less complete than Topaz, but the interface itself looks very much like Topaz. It is more plagiarism than inspiration. Even the icons are identical.
)
