AI video upscaling redraws detail a resize can't, and it's a guess every time
AI video upscaling raises a video's resolution by redrawing the fine detail a smaller frame can't hold, using a neural network trained on pairs of sharp and degraded images. A plain resize only spreads the existing pixels further. We measured the difference by halving real frames and upscaling them back. A plain resize kept the exact pixels and colours best but restored under two thirds of the fine detail. A heavier AI model restored up to 96% of it, by drawing detail that looks right rather than detail that was there.
The problem it solves
A 480p frame is 640×480, about 307,000 pixels. A 4K frame is about 8.3 million. Going from one to the other means producing 27 pixels for every 1 you started with, and no arithmetic recovers information that was thrown away when the video was shot or compressed. The only question is what goes in the empty space.
A traditional scaler fills it with a weighted average of the neighbouring pixels. Bicubic and Lanczos differ in the weighting, not the idea, and the result is soft, because a blur is the safest guess when you know nothing about what the picture contains.
What the model does differently
A super-resolution model is trained on enormous numbers of image pairs: a sharp frame and a degraded copy of it. It learns what a real brick edge, an eyelash or a line of text looks like at full resolution once it has been reduced to a few grey pixels. Shown your footage, it doesn't average. It produces the most likely sharp frame, given everything it has seen.
That is why the result has crisp edges and texture where a resize gives a smooth smear. It is also why it is a guess. Never treat upscaled footage as evidence of what something looked like: a model will happily draw a sharp, confident, wrong licence plate.
What we measured
To score a guess you need the right answer, so we made one. We took four frames: three from real aerial footage and a card of text and hard-edged colour. We halved each, then enlarged it back 2× four ways: a plain Lanczos resize, a fast 2× AI model, a heavier detail model, and that detail model's denoising version (what Crisp's Denoise 0.50 setting selects). Each result was scored against the original frame. Everything ran on unencoded frames, so no video compression favours either side.
| Frame | Method | Fine detail restored | SSIM | PSNR | Colour shift (ΔE) |
|---|---|---|---|---|---|
| Overhead architecture | Lanczos resize | 45% | 0.907 | 27.8 dB | 0.1 |
| Fast 2× model | 58% | 0.855 | 25.7 dB | 1.6 | |
| Detail model | 96% | 0.893 | 25.0 dB | 0.7 | |
| Detail model, denoise version (Denoise 0.50) | 86% | 0.901 | 26.4 dB | 0.9 | |
| Snowy town at dusk | Lanczos resize | 47% | 0.916 | 29.9 dB | 0.1 |
| Fast 2× model | 59% | 0.853 | 26.4 dB | 2.8 | |
| Detail model | 95% | 0.886 | 27.0 dB | 1.4 | |
| Detail model, denoise version (Denoise 0.50) | 87% | 0.888 | 28.1 dB | 0.9 | |
| Forest river | Lanczos resize | 31% | 0.824 | 24.6 dB | 0.1 |
| Fast 2× model | 36% | 0.694 | 22.6 dB | 1.2 | |
| Detail model | 47% | 0.789 | 23.6 dB | 2.4 | |
| Detail model, denoise version (Denoise 0.50) | 52% | 0.760 | 23.5 dB | 1.9 | |
| Text and graphics | Lanczos resize | 64% | 0.939 | 20.7 dB | 0.3 |
| Fast 2× model | 63% | 0.882 | 19.8 dB | 2.3 | |
| Detail model | 70% | 0.945 | 20.6 dB | 0.8 | |
| Detail model, denoise version (Denoise 0.50) | 67% | 0.947 | 20.8 dB | 0.8 |
How to read it. "Fine detail restored" compares the edge energy of the result with the original's. SSIM (structural similarity, 1.0 is identical) and PSNR (higher is closer) measure how exactly the pixels match. Colour shift is blurred ΔE76, where about 2.3 is the smallest difference people see.
Why the numbers disagree
The plain resize has the highest PSNR on three of the four frames and the highest SSIM on three, and it barely touches colour. It is the most faithful because it invents nothing. It is also the softest, restoring 31% to 64% of the fine detail.
The detail model restored far more, 95% to 96% on two of the aerial scenes, and beat the resize on SSIM for the text card. It scores lower on PSNR anyway, because PSNR punishes detail that is plausible but not exactly where the original had it. The dotted ring drawn solid in the figure is that trade, visible.
The fast model is the honest disappointment: it restored only a little more detail than the resize, and on the text card slightly less. Speed is what it buys. On a Mac Studio it took roughly half the time per 4K frame that the detail model did.
Scope, plainly: four frames, 2× only, one machine. These compare methods on the same frames. They aren't constants for your footage.
What it genuinely fixes
| Problem | Fixable? | Why |
|---|---|---|
| Low resolution | Yes | The core case. Detail is missing but structure survives. |
| Compression damage | Mostly | Blocking and banding have consistent shapes a model can learn. |
| Sensor noise and grain | With care | Denoise first, or the model sharpens the noise into texture. |
| Out-of-focus or motion blur | No | The information is gone from every frame. See why AI upscaling can't fix focus. |
Frames are not photos
Upscaling one photo is a solved problem. Upscaling 1,500 frames in a row is not, because each frame is processed on its own and the model's guesses differ slightly from one to the next. A texture drawn one way on frame 200 and slightly differently on frame 201 shimmers: a crawling quality in flat areas, obvious in motion and invisible in a still. So judge any upscaler playing at full size, never on a paused frame.
What Crisp does
Crisp ships both kinds of model and picks one per job. Enhance at 2× uses the fast 2× model, and at 4× it uses the detail model. "Enhance to 4K" on a 1080p clip is a 2× job, so it uses the fast model too. Asking for stronger noise reduction switches to a denoising version of the detail model. From Crisp 1.0.1359 (23 September 2026) the fast model's output takes its colour from your original, because on its own it shifted colour visibly; the colour shifts in the table above were measured with that fix in place. Everything runs on your Mac.
Getting the detail model at 2× today
You can, with one setting. In Advanced, set Denoise to 0.50. At exactly 0.50 a 2× job switches from the fast model to the denoising version of the detail model, with no extra noise filter; above 0.50 Crisp also adds a noise pre-pass, which smooths detail away. In the table that setting restored 86% to 87% of the fine detail on the two aerial scenes, against 58% to 59% for the default, with better SSIM and PSNR than the default on all four frames. It costs time: about 1.2 seconds a 4K frame against about 0.8 on a Mac Studio, roughly half as long again.
What to do with a bad clip
- Work out which problem you have. Pause and zoom in. Soft everywhere, with no hard edges anywhere, is focus, which can't be fixed. Square blocks in dark or fast-moving areas are compression, which can.
- Deal with noise as part of the upscale. Upscaling noise teaches the model to treat grain as texture and amplify it.
- Compare against a plain resize. If a Lanczos resize looks acceptable for where the video is going, it is free and the most faithful. See when AI upscaling beats a plain resize.
- Judge in motion, at full size. Shimmer only shows when it plays.
AI upscaling questions
What is AI video upscaling?
Raising a video's resolution with a neural network that redraws fine detail, instead of only spreading the existing pixels further as a normal resize does. The network is trained on pairs of sharp and degraded images, so it produces the most likely sharp version of each frame.
Is AI upscaling better than a normal resize?
It restores more detail and is less exact. In our test a heavier AI model restored up to 96% of the original's fine detail, against at most 64% for a Lanczos resize, but the resize matched the original's pixels and colours more closely. For a sharp source going to a larger screen, a resize is often enough.
Does AI upscaling recover the real detail?
No. It draws detail that is plausible for what the frame shows, not detail that was recorded. In our test it redrew a dotted ring as a solid one. Never use upscaled footage as evidence of what something looked like.
Can AI upscaling fix a blurry video?
Not if the blur is from focus or motion. That information is gone from every frame, and the model sharpens the blur rather than removing it. Low resolution and compression damage are what it fixes.