Noise reduction remains one of the slowest parts of compositing. Whether you’re cleaning plates, prepping greenscreens, or integrating CG inside Nuke, denoising can stall entire pipelines. The freshly released Neat Video 6 tackles that: doubling render speed, halving memory usage, and managing CPU/GPU optimization automatically.

Automatic Performance Tuning

Older Neat Video versions required users to manually enable GPU acceleration and tune performance settings. Version 6 eliminates that setup hassle: it detects available CPUs and GPUs, distributes load dynamically, and adjusts on the fly when resolution, effects, or system load change.
For compositors, that means smoother playback, faster previews, and less downtime during roto or cleanup work.

CPU + GPU Optimization

The new Fast Floating Point Processing mode speeds up rendering without sacrificing image quality. Neat Video’s re-engineered engine now performs parallel processing alongside the host app, reducing idle time in complex Nuke scripts. Depending on system specs, artists can expect up to 2× faster output compared to version 5.

Memory Efficiency for High-Res Comps

Compositors working on 4K–8K plates will notice the difference: Neat Video 6 uses up to 2× less RAM / VRAM and dynamically adjusts GPU memory use. That means fewer slowdowns, fewer GPU crashes, and less reliance on SSD-based virtual memory, extending both performance and hardware lifespan.

HDR Accuracy and Premiere GPU Integration

Neat Video 6 introduces an adjustable gain control that improves denoising on HDR or underexposed footage. Premiere Pro users benefit from a new GPU data exchange path that sidesteps the notorious Lumetri slowdown, cutting render times and avoiding color pipeline mismatches.

Hardware and Platform Support

The update supports Apple Silicon M4 systems and NVIDIA RTX 50-series GPUs, and is available for Nuke (OFX), Premiere Pro, DaVinci Resolve, and After Effects on both macOS and Windows. Give the trial a whirl here.

Pricing

• Home edition – Full HD, 1 GPU, non-commercial use, from $80
• Pro edition – Unlimited resolution, multi-GPU support, commercial use, from $130

Conclusion

Version 6 is less about shiny new buttons and more about workflow sanity: automatic optimization, leaner memory use, and shorter render queues. For studios knee-deep in Nuke scripts, that’s enough reason to take notice.

Read more: Official release thread on Neat Video Forum

The post Neat Video 6: Smarter Noise Reduction for Nuke and Beyond first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

Source: Blackmagic Pocket Cinema Camera 4K

Or in short, the BMPCC 4K, is the first camera by BM to get the option of shooting ProRes RAW (PRR in short) by installing the 9.8 Public Beta firmware. Not a big risk, since you can always go back if that beta is not performing as expected. Filmmaker Christoph Janetzko from Berlin has kindly sent us a few samples to compare, shot at maximum quality in BRAW Q0 and ProRes RAW HQ (PRR for short) under identical conditions. We wanted to have a closer look at resolution and noise, since BRAW is based on partial debayer and ProRes RAW might retain some more information.

Shooting conditions and metadata

Both were shot at full DCI 4K from the sensor in 25 fps, which generated around 1.150 mbps in PRR, but only around 878 in BRAW. This is for identical scenes, in this case the focus chart, but these codecs are quite adaptive to image detail. For resolution, both were shot with a Minolta 50mm/1.4, stopped down to f5.6. It’s vintage, but still a damned sharp lens.

The clips show more metadata in both formats than the iPhone 17 in our recent test, like shutter speed (or angle), of course no focus data from a manual lens. What is missing in PRR, even from electronic lenses, is gyroscope data. In BRAW, these work with manual lenses too, if you remember to set the focal length in the camera.

Resolution and noise

Some users claim that BRAW is pre-filtering the image to improve compression, which might lead to loss of detail. From our test chart, we could neither prove that, nor a tendency towards aliasing with the unfiltered PRR footage. From the start, they look a tiny bit different, even if both decoded as BMD Film generation 5 (which can’t even be changed for the PRR clip). After some minor corrections of contrast and luminance, they look virtually the same, even as a 2x center crop. There’s also no aliasing with the unfiltered PRR shot. Can you tell the difference? There was no correction of colors applied.

For the noise test, we underexposed considerably, but of course identically. This camera has been around for a long time, and it’s not really a low-light monster. We raised the ISO from the recorded value of 400 to 1.000, which is the maximum for BRAW. ISO can be raised to 25.600 for PRR, but that would be a ridiculous level for these shots. Instead, we had BRAW raised by another stop with the Exposure slider, and raised PRR to a similar level in the waveform. BRAW is offering 5 stops here, while PRR has just one.

What’s missing for PRR shots in the RAW tab: the tint slider, white balance presets, and the Highlight Recovery option. A correction for the tint axis in particular would be desirable, our camera would have needed about +10 for either clip, but that can easily be corrected elsewhere in DR. If your clips were recorded externally with a Ninja V, some cameras and their color space plus gamma are identified, but adjustments are also very limited.

These shots confirm some mild pre-filtering in BRAW, resulting in a much smaller noise floor. So, at the cost of around 30% higher data rates, maybe there’s a tad more detail from PRR in the shadows. Sensors with more photocells may expose more of a difference, but I’d say this is still a matter of taste, not only storage space. Some may appreciate the mild softness of BRAW. With some noise filtering applied (more on that below), PRR can look cleaner than unprocessed BRAW. This also proves that the pre-filtering in BRAW is quite restrained. Of course, you can also filter BRAW if needed, but that needs extra time.

Denoising compared

Looking at those extreme night shots in part one and noticing that new ML Denoise feature in Apple’s Compressor, we decided to compare with Neatvideo 6 (NV 6 for short) and with the internal noise reduction in DaVinci Resolve (DR for short). Of course, next to image quality, speed is crucial, since none of the best denoisers is realtime. It has been a while that we evaluated Neatvideo 5, which has always been our “go to” solution for noisy footage. We have prepared 5 second clips at an ISO of 8.000 in ‘small’ HD (1.280 x 720) to compare, which you can download from a Google Drive. The first, without any NR, is just below. These are 1:1 center crops from the main camera of the iPhone 17, as seen in our last article. Please download the following ones and play as a loop to judge the quality.

No Noise Reduction – the orignal

Straight outta Resolve

Here Comes Compressor

With Neatvideo

NV 6 has been improved a lot on Apple silicon, we measured a speed advantage of 75-80% over version 5 under optimal conditions: rendering from the internal SSD to a Thunderbolt NVMe drive. The CPU cores get to full load, the GPUs nearly as much, while rendering at close to 8 fps in DCI 4K. You can hardly squeeze more out of a Mac mini M4 Pro. Memory usage for even larger frames has also been improved. Image quality was impressive, as usual, even if you’d not really want to use footage as dark as our sample without having documented Mafiosi fighting in the shadows (and gotten away with it). Or without grading it as a night shot, as we did.

Apple’s ML Denoise, which works only with iPhone footage and is only available in Compressor 4.11 up to now, did a pretty good job. It needed about twice as long as NV 6, rendering with the GPUs only, while using the full open gate resolution, so you could get some vertical wiggle room out of it. On a serious Mac Studio with 60 GPU cores it should fly, but Neatvideo might get close to realtime on that. We found the results quite impressive, but only the setting Low is preserving enough texture on the street, for example. Medium and High look too plasticky, and there are no other adjustments. But if you use an iPhone 17 anyway, it’s not too expensive at 50,- US$ for a license without time limit. You’ll have to live with watch folders and batch processing, instead of integration with DR, though.

DR’s internal NR features can get pretty close in quality to NV 6 with careful fine-tuning, as explained in this tutorial by Darren Mostyn. But NV 6 offers better tools for very precise adaptation to your footage. It is highly adjustable and integrates with DR, while Compressor only co-operates with Final Cut Pro (of course). And then, DR is more than two times slower, using only the GPU cores, at similar settings (better or high in either software). Image quality might be even better with AI UltraNR, but that is unbearably slow if you don’t own a high-end Nvidia GPU. Finally, if there is too much noise in your sources, the software solutions don’t turn PRR noise into pretty grain, it gets blotchy in the darkest areas, just like from other cameras. Better add some convincing grain, if needed, but watch your final compression.

Conclusion

Footage in ProRes RAW out of a BMPCC 4K demonstrates the quality and malleability of the format in DaVinci Resolve, even if a few parameters are still missing. But there is not much of a reason to switch, since the same footage in BRAW is just as good, if not better in the shadows, and you save space with it.

Footage from the iPhone 17 at low light is impressive for such a tiny sensor, and it cleans up pretty well with a good denoiser if needed. It should not stand out in a negative way when used in a major production. But be aware that this is still quite new, so expect bugs or missing features, like those reported in forums for most of the camera apps currently recording the new codec.

P.S. The first chart on top is from ProRes RAW.

The post ProRes RAW vs. BRAW first appeared on DIGITAL PRODUCTION and was written by Uli Plank.

Neat Video has released version 6.0.5 of its well-known noise reduction plugin, aiming to further polish workflows in post-production, VFX, and editing. While this is a maintenance update, it brings notable improvements across several areas.

GPU Management: Now With Extra Brainpower

The GPU Management system inside Neat Video has been fine-tuned. Specifically, Neat Video 6.0.5 improves the matching of multiple GPUs when using a mixed set of graphics cards. In plain English: if your setup looks like a hardware flea market, Neat Video now juggles your GPUs with a little more grace. No new devices added or dropped—just better teamwork among the existing hardware.

Color Channel Corrections: Less Magenta, More Reality

Neat Video 6.0.5 fixes an issue where subtle color channel biases could sneak into the denoised output. Translation: if your highlights were starting to look suspiciously pink or green, the update promises a more faithful reproduction of colors after noise reduction. So, goodbye uninvited magenta, hello proper white!

Pricing and Availability

Neat Video is available directly through ABSoft. Pricing depends on the specific platform and plugin host you choose (After Effects, Premiere Pro, DaVinci Resolve, etc.), so check the official shop for details.

Production Readiness: Proceed With the Usual Caution

While Neat Video 6.0.5 brings welcome improvements, any plugin updates—especially those related to GPU management and color processing—should be thoroughly tested within your pipeline before being deployed into live projects. Because nothing says “unplanned overtime” like a sneaky update glitch halfway through a client delivery.

---

The post Neat Video 6.0.5: Noise Reduction Gets a Patch-Up first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

In addition to the previous capabilities in upscaling and de-interlacing, changes to the frame rate up to slow motion, stabilisation (still in beta) and noise reduction are now offered. There is a command line control and the programme should have no problems with variable frame rates, as is often the case with smartphones and computer recordings.

GUI

Despite all the technical performance, the user interface still seemed a little clumsy, but Topaz Labs has thoroughly tidied things up here. Batch processing in particular, including processes running in parallel, has become much clearer. It can now be organised according to previews and export tasks and their status as well as well-estimated remaining times are visible at first glance. If several variants are to be created from one original, this is also unproblematic. Unfortunately, it is not yet possible to change the order in which the tasks are to be processed, which would be useful for the lengthy calculations.
The selected processes and their parameters are displayed on the right, with useful presets and brief explanations of the properties of the respective AI models. To do this, you must leave the cursor on the headline or the respective icon, not on the word itself. For the output, you can choose from all containers and codecs that ffmpeg can handle, as this is what TVAI is based on. Accordingly, hardware encoding of H.264/265 is also offered if the computer supports this.
In addition, very high-quality video formats with a large bit depth are also available, for which you previously had to output image sequences from Video Enhancer AI. However, this also means that a codec such as ProRes is not the original version, but the version from the free programme that is not authorised by Apple. Technically, this is not usually a problem, but some customers may find it annoying.
A number of models and filters can be combined. But you can’t stack every combination, e.g. you should perform high-quality de-interlacing with “Dione” and only then apply optimum upscaling to the result with “Proteus”. The imported material can be trimmed to a desired area using “Trim”, but unfortunately the timecode of the original is not displayed, which would of course be very helpful in the workflow. This could probably be easily changed, because if TC is present in the source, it is passed through to the final product.

You can also crop the source, as is necessary for the thin lateral bars of DV or the blanking interval of analogue sources. The pixel values are displayed precisely. TVAI also recognises the format of non-square pixels if the corresponding flag in the source is correct. The programme cannot handle inverse telecine (i.e. the removal of redundant fields in NTSC film copies), but any good editing system today can do this in a flash.
The selection of the appropriate AI model is simplified by optimised suggestions, with some you can no longer intervene at all, but you don’t have to. So far, TVAI does not save any projects and their settings, which is why you are only asked whether you mean this first when you exit the programme. As long as the programme is rendering in the background, there is unfortunately no progress bar under its icon. If you need the computing power for something else, you should simply stop running processes and leave the programme open in the background.
Any malfunctions are only displayed with a red X next to the process at first glance, but clicking on it leads to a more detailed explanation. The calculations ran reliably during testing with version 3.0.3, there were only two minor issues. During output (here always in ProRes 422 HQ), the first image was black and was displayed as offline in DaVinci Resolve. When de-interlacing, the first few frames were black. In addition, the entire GUI sometimes flickered during the calculation.

De-interlacing and scaling

The programme naturally continues to perform the original main task of upscaling. The AI models recommended for this are comprehensive and quite varied. “Gaia”, for example, has only two fixed presets for high-quality sources or for computer graphics, while “Artemis” has five for material of varying quality. When an AI model is used for the first time, TVAI first has to download it, which can take a while depending on the internet connection. Later, the saved models are used and the internet connection is no longer necessary.
This can add up to quite a lot; by the end of the test, we needed a good 2.7 GB of space. The models “Theia” and “Proteus” (incidentally, these are all figures from Greek mythology) can be adjusted in
The models “Theia” and “Proteus” (incidentally, these are all figures from Greek mythology) can be adjusted in detail, e.g. to reduce compression artefacts, moiré or noise, to sharpen the images or to add some structure as noise or ‘grain’ to overly smooth images. Proteus even offers the option of analysing the material and suggesting suitable slider settings.
Of course, we were not able to test all models for all types of sources, and certainly not with all adjustment options. We tested two types of typical sources from the early digital era, both with interlace. One source was in DVCAM in PAL format of 720 x 576 from a semi-professional camera with an aspect ratio of 4:3. The other was HDV in 1080i with 1440 x 1080, i.e. a pixel format that also has to be ‘stretched’ for 16:9. In both cases, the digitally copied original was read by TVAI without any problems.

In our early test of Video Enhancer AI, we still had to work with tricks, but now the programme is capable of de-interlacing. However, this function is not offered automatically based on the flags. We first had to switch to “Interlaced” under “Video Type”, but then TVAI does an amazing job. It automatically converts the PAL recordings to 50 fps so that the temporal resolution is retained and always uses a variant of the “Dione” model for this.

What came out of our DVCAM source in HD is quite impressive. It was not a drone shot (which did not exist for civilian purposes at the time), but a handheld camera in a helicopter. No other de-interlacer was able to handle the particularly critical parallel line structures on the buildings like TVAI. Only in the case of short, fast vibrations did the motion blur prevent an optimal reconstruction of the contour lines. However, a trial with scaling to UHD led to results with a manga look.

As a cross-check, we also scaled down a clip in UHD from a high-quality camera to SD (to 1024 x 576) with minimal compression and ‘blown up’ it again with TVAI. It looked quite decent in HD, but no longer in UHD. In parts of the image, the AI then invented structures that did not even exist in the source. The rest was not pixelated, but blurred. Even if the software offers much more extreme scaling, we would consider this to be of little use. Especially as modern TVs scale so well from HD to UHD that it hardly bothers you at a normal viewing distance.

For comparison, we ran the material through the ‘neural’ de-interlacer in DaVinci Resolve Studio (DR for short) and upscaled it with its SuperScale. While differences in the scaling
were only recognisable on very close inspection, the de-interlacing was significantly weaker. Only the freeware QTGMC, which we had already tested at the time, comes close to the results from TVAI, but is somewhat cumbersome in professional practice. The results from HDV, especially with natural textures, are also impressive in UHD. The de-interlacing was just as flawless here.

Intermediate images

Since, according to Topaz Labs, TVAI also obtains the reconstruction of details from the neighbouring images, the generation of additional images for slow motion or format conversions (e.g. 24 to 50 fps) was obvious. The programme suggests “Chronos” as the AI model for an extension up to four times, and “Apollo” for even higher values. However, you can also choose freely between these models. Chronos Fast” does not calculate faster, but is supposed to recognise fast movements better; Apollo actually calculates a good 20 percent faster.

Which is better in terms of results seems to depend more on the subject. To compare the quality, we again used the studio version of DR and set the “Speed Warp” algorithm under “Optical Flow”. You won’t find this in the project, but only in the “Inspector” for the individual clip. Although it also works slowly, in our experience it is usually the best option for slow motion. The results are difficult to distinguish from each other if the DV material has previously been freed from interlacing with TVAI.

On closer inspection, both methods have similar problems with overlapping movements or the dragging of parts of the background, and yet both are clearly superior to the common optical flow methods. These errors will hardly be noticeable to an untrained observer for many motifs. The calculation times do not differ drastically here, Apollo is around 6 per cent slower than Speed Warp.

The slowing down of a drone shot over a rice field was very interesting. It was actually a series of individual images that were to be stretched as a sequence. Both programmes produced excellent results with a vertical movement. However, with a transverse movement, in which the motif was characterised by many repetitive structures in the plants, both failed and produced almost identical artefacts. There’s nothing like real slow motion from the camera; in all other cases, success is heavily dependent on the subject.

Image enhancement

Yes, they still exist, the small improvements through “enhancement”, primarily with Proteus. It is designed to reduce compression artefacts and noise and bring out real details. We tried it with deliberately over-compressed and not entirely noise-free material that had previously been run through an H.264 encoder in UHD at too low a data rate. But the results require a lot of “pixel peeping” to see the progress, and one wonders whether this justifies computing times by a factor of 10 to 20 on hardware that isn’t quite weak.

Another test for noise reduction alone was carried out with Artemis, this time with high-quality footage from a Blackmagic 12K, but in very low light. For comparison, we used Neatvideo as the current ‘gold standard’ in the lower price range. Both programmes were quite good at bringing out real detail and significantly reducing noise. But Neatvideo was once again able to do it better, in particular Artemis left a slightly coloured and cloudy unsteadiness over the entire image. This phenomenon was hardly present in Neatvideo, which is probably due to the differentiated processing of individual frequency ranges with the help of specific samples.

In addition, Artemis only has three settings for low, medium and high noise (plus halo removal if required). In none of them were we able to remove enough noise without the surface clutter appearing. Neatvideo, on the other hand, was already better in the standard setting, without us having to resort to the highly differentiated adjustment. It is almost seven times faster.

Stabilisation

The new version also offers stabilisation of nervous camera movements, and even the correction of artefacts through rolling shutter or the reduction of jitter can be optionally activated. No special AI model is responsible for this, but the function simply appears under “Filters” (still in beta). The results with “Auto-Crop” are already very decent, even if some ‘jelly’ from the rolling shutter occasionally remains. However, our test material came from a camera with a rather slow readout of 30 milliseconds.
The alternative is called “full-frame”, where the missing image content in peripheral areas is filled in with offset material from neighbouring images. This works surprisingly well at times, but occasionally very poorly with short bursts. A slight artefact of this kind can even be seen in the Topaz tutorial. As such interference in peripheral areas distracts a lot from the film, the crop version plus upscaling should generally look better.
We compared the stabilisation results with the function from DR, with the “Perspective” setting. This is quite similar in terms of quality, with slight image distortions remaining here too. The processing times are acceptable in both cases if you do not activate Full Frame or Reduce Jitter in TVAI
Again. However, neither method can achieve the level of stabilisation based on gyro data that some cameras from Blackmagic or Sony provide (see DP 06:22).

Hardware requirements

Our tests were carried out on an Apple M1 computer, which is not exactly optimally equipped for this, even if TVAI is already running natively. Although the computer is well used, neither the CPU nor the GPU are fully utilised. We compared the times on an Intel computer with 580 GPUs (AMD) as a test, which cannot keep up with the M1 laptop under DR despite the second GPU. With TVAI, however, the older iMac was significantly faster. The eGPU didn’t play such a big role here; with the internal GPU alone, the times were only around 20 per cent longer.
In most cases, however, the computing times are miserably long, apart from
pure de-interlacing, which should achieve real time on more powerful hardware than ours. Even though TVAI can now use all GPU families, it is primarily at home on Nvidia. For comparison on our computer: Creating a quadruple slow motion from the clip of the Mexican carnival took an hour and 45 minutes with TVAI. SpeedWarp and SuperScale took 6 minutes and 23 seconds. The visual result was by no means so drastically superior.

Commentary

You shouldn’t expect miracles: A recording from 1998 from a very respectable DVCAM from Sony at the time doesn’t look really good in UHD, even with Topaz Video AI. The highest of feelings is reasonably usable HD, whereby the astonishingly good de-interlacing contributes even more to the result than the actual upscaling. The software can also turn HDV with non-square pixels and interlacing into reasonably presentable UHD.
That’s it, and anyone who needs this more often to save their audiovisual cultural heritage should buy a PC with the most powerful Nvidia card, with which you can also heat your study until the next blackout. Faster software such as DaVinci Resolve can do slow motion or stabilisation almost as well, the latter with gyro data even better. For noise filtering, Neatvideo remains
remains unbeaten.

The post Saving audiovisual cultural heritage with Topaz Video AI 3.0 first appeared on DIGITAL PRODUCTION and was written by Uli Plank.