Here is an example of what I am trying to achieve when I upscale. Just a bit cleaner with less noise, not a miracle hidden Blu-ray video.
2 Likes
At least for now I would like to still use 2.6.4 until the speed is fixed. Is there somewhere I can download 2.6.4 from?
I think people tend to over expect what VEAI can do. Iâve always said and will continue to say that computing technology/AI capabilities are many years away from being able to take and old VHS/PAL video and upscale it to a quality equal to content originally shot in native 4K. If we weâre at that point today, I wouldnât be upscaling Star Trek Voyager for the third time, because Paramount Studios would have done it already. VEAI is a hobby and gives me something to do in my off hours.
3 Likes
absolutly !!!
Cheapens? Lots of folks prefer MKV, myself included. Simply select the MP4 output option and your good to go.
2 Likes
I donât know that I would call VEAI a hobby as professional restorers I think would see it as just one more tool in there toolbox. For individuals yes a hobby but they expect perfection for the price of what is just another tool. As an electrical/RF engineer by trade the cost of VEAI seems like such a bargain for what it does. From a hobby stand point VEAI is expensive but one must prioritize their needs. Never buy software that is not meeting your needs at the moment and never buy software based on what you think it will become.
1 Like
I only say this because it appears this software is going to more of a consumer market rather than professional. Iâd gladly pay twice the price for improvements.
V3 is a disaster - it should stay in Beta until it is well tested and improved. I think the price is lower too at $159. I paid $299 a year ago. To me this is not looking like a professional tool for producers anymore. I had high hopes that V3 would be an improvement in speed and quality but Iâm not seeing that.
Just my opinion. They are trying to find their market and competition is coming quickly. Plug-ins for After Effects are already here.
If you are a first time buyer - you will be getting v3 and not the more stable v2.6.4. I think there is a deeper reason for the total rewrite.
Time will tell. I remain optimistic.
4 Likes
Yes, for me itâs just a hobby, so I can only speak for myself. If your in it to earn an income, then I suppose it can be viewed much differently.
For now, I agree this would be more for the tinkering type, like myself, but I wouldnât describe it as a disaster, but more of an evolutionary thing. I think the potential is there to upscale old video to native 4K, but not for many years to come. Look at computing technology in the 1950âs and compare it to what we have today. This applies to all emerging technologies, not just AI and video upscaling.
It looks nice and has a lot of new features previously promised.
But performance is a total failure. In my case, version 2.4.0 is the fastest, 2.6.4 is about 10-15% slower, and 3.0⊠well.
3.0 wants more CPU resources to perform the same or worse than 2.6.4.
This premiere took place definitely prematurely.
(5800X, RTX3090)
3 Likes
Iâve been testing the new version and I can say I like it so far, because it has more codecs, more ai models to choose from and they actually all look different compared to each other.
BUT!
I found out that ARTEMIS works worse. I tested a .mov I upscaled in 2.6.4 with artemis high quality and it looks much better. More shadows in the noisy areas preserved while 3.0.0 just blurs these areas and causes detail loss. UnfortunateâŠ
Yes, I also have the feel that the new version dropped in its ability to recover details. As mentioned earlier I think the early Artemies models were better in recovering details. These are still included in the de-halo modes, but de-halo in addition adds a dreamy look so it is not exactly what were early Artemies modes like!
VEAI supports only 2x or 4x scaling, other scales are scaled by lanczos.
In the veai_up filter, there is a scale option and w,h option. If w,h is set when scale=0 (or not set), the scaling factor is automatically calculated internally, and âscale=2â is applied if w or h is larger than 1.2x, and âscale=4â if w or h is larger than 2.4x. scale=4" is applied internally.
For example, in the case of 720x480(wide) â 1280x720 proteus, the show export command will result.
-filter_complex veai_up=model=prob-3:scale=0:w=1280:h=720:preblur=0:noise=0:details=0:halo=0:blur=0:compression=0:estimate=20:device=0:vram=0.9:instances=1,scale=w=1280:h=720:flags=lanczos:threads=0:force_original_aspect_ratio=decrease,pad=1280:720:-1:-1:color=black
This is internally equal to setting scale=2.
-filter_complex veai_up=model=prob-3:scale=2:preblur=0:noise=0:details=0:halo=0:blur=0:compression=0:estimate=20:device=0:vram=0.9:instances=1,scale=w=1280:h=720:flags=lanczos:threads=0:force_original_aspect_ratio=decrease,pad=1280:720:-1:-1:color=black
So the flow is
720x480 â veai 2x scale(1440x960) â lanczos resize(1280x720) â padding black
The scaling factor calculation also takes the aspect ratio into factor, so there are cases where the image is scaled only by lanczos instead of the expected scale setting, which I think is causing confusion.
In the alpha version, there were no w and h options, and scaling factor calculations were done on the GUI side, so it was obvious at a glance how many scales had been set by looking at the options in the log.
2 Likes
@ida.topazlabs @nipun.nath @gregory.maddra
Until this release, I have limited myself to using the VEAI 3.0.0x betas. IMO, they were vere weak in the areas of cleanup - denoise decompression and deinterlace, (especially, deinterlace.)
As you have been doing regardless of source, my working output from VEAI is always ProRes 422 HQ.
In the new officially released version of VEAI 3.0, they have very much improved the output of noise cleanup and artifact removal, but there is still a curious âsawtoothâ pattern on the right edge of the image. (Iâm deinterlacing wide-screen video from a 4:3 SD source)
I wonder if this is due to a difference in the actual number of pixels or dots in that odd/even lines deinterlace (TV x2 dehalo) performs. It also makes me wonder whether there are latency issues and whether the odd/even lines in the output are out of scale all through the left to right scan. - There are several places where I can see what may be the earmarks of this problem. In several places it is obvious that horizontal lines often âbleedâ into adjacent solid colored areas. It often loses subtle stripes on horizontal fabrics, extends eyebrows and creates more patterns on checkered areas.
Theyâve fixed a lot of the noise and artifact issues, but numerous defects above still remain.
As for the Enhancements, especially Proteus, they are capable of doing some very good work, - That is; provided you can feed them clean material. This is especially true if the inputâs colors are not overly saturated. Oversaturation can make it difficult to recover detail in small, similarly-colored areas and then some detail disappears.
IMO: VEAI 3.0 is a major advance from previous versions, but a lot of it still needs refinement.
3 Likes
âIMO: VEAI 3.0 is a major advance from previous versions, but a lot of it still needs refinement.â
yes, full dâaccord!
It would be helpful to avoid misunderstandings if the weekly releases could follow a given roadmap of prioritized âknown issuesâ .
Actually releases appear total random what gets delivered. Welcome in the VEAI improvement lottery! Evolution by try&error thatâs AI.
Digitized SD video does not use square pixels, with NTSC at 720x480 they are 8/9 pixels for 4:3 and 32/27 for 16:9. So 640x480 is correct if the pixels have been converted into square and itâs a 4:3 aspect ratio. (16:9 is usually translated to 853x480 but some software uses 854x480).
Non HD video in PAL does this as well.
2 Likes
Well, thatâs life; trial and error. - In the digital world itâs called debugging.
This quoting does not replay Imoâs words. 
