Get the newsletter
Nvidia · AI / ML · Filed Jan 21, 2026 · USPTO published Aug 13, 2026 · Aug 13 release

Nvidia Patents a Two-Stage Video Compression System That Avoids Quality Degradation

Nvidia has patented a video compression architecture that gets 8 times the compression rate of conventional approaches by letting each video frame learn from the raw, uncompressed version of the frame before it, rather than a degraded copy.

Side-by-side comparison of a compressed still image and a multi-frame video sequence processed by tokenizers. Drawing from patent filing US 2026/0237209 A1.
Side-by-side comparison of a compressed still image and a multi-frame video sequence processed by tokenizers.All 14 drawings ↓
Publication number
US 2026/0237209 A1(US20260237209A1)
Applicant
NVIDIA Corporation
Filed · Published
Jan 21, 2026 · Aug 13, 2026
Inventors
Songwei Ge, Xian Liu, Jinwei Gu, Haoxiang Wang, Fitsum Reda, Ming-Yu Liu, Yogesh Balaji
Status when we published
Waiting for an examiner
Document
26 claims
US classification
382/159
Parent application
Claims priority from a provisional application 63756542 (filed Feb 10, 2025)

How Nvidia's two-stage video tokenizer cuts file size

Ever tried to stream a high-resolution video only to watch it turn to mush the moment your connection dips? A lot of that quality loss happens before the video even reaches your screen, during the step where AI systems chop footage into compact chunks for processing or storage.

Nvidia's patent describes a system that handles this chopping in two stages. The first stage handles the visual basics, squeezing raw pixel data down to a manageable size. The second stage goes deeper, looking for patterns across frames the way you might notice a slow pan or a recurring background and compresses those patterns too. The key trick is that the second stage feeds each new frame a clean, pre-compression signal from the previous frame instead of an already-degraded one.

The result, according to the filing, is that the system keeps improving the more you train it, whereas older approaches hit a ceiling and stop getting better. That kind of scalability is exactly what you need when you are trying to build AI video tools that work on hour-long footage, not just short clips.

From the filing · CLAIM 1
generating a set of first tokens of frames of a video using a convolutional tokenizer in a pixel space, wherein the set of first tokens corresponds to a perceptual compression of the frames of the video; freezing the convolutional tokenizer from further processing …

Translation: The system first compresses video by turning images into digital tokens and then locks that part of the process in place.

Inside the convolutional-then-transformer encoding pipeline

The patent describes what Nvidia calls an autoregressive (AR) video tokenizer, a system for converting video into compact numerical codes (tokens) that an AI model can work with efficiently.

Most existing tokenizers compress a video frame by frame in isolation, then bolt the frames back together. This one uses a two-step pipeline:

  • Stage 1 (convolutional tokenizer, pixel space): A standard convolution-based network (think of it as a pattern-finding filter applied to raw pixels) compresses each frame into a mid-level representation called a perceptual token. Once this stage finishes, it is frozen and not updated further.
  • Stage 2 (video transformer tokenizer, latent space): A transformer network (the same class of architecture behind large language models) takes those mid-level tokens and compresses them further into semantic tokens, using context from previous frames. Crucially, it uses the pre-compression signal from prior frames rather than the already-quantized (digitally rounded) version, preserving more information.

The phrase temporal causality here just means the system treats video the way it actually works: frame 47 is shaped by frame 46, which is shaped by frame 45. By wiring that dependency into the compression step, the system avoids re-encoding information that hasn't changed, which is most of any given frame in most videos.

The filing claims the architecture continues to improve as training compute scales up, a property it contrasts with conventional discrete tokenizers that plateau. That scaling behavior is the central engineering claim.

From the filing · THE ABSTRACT
By bypassing the quantization layer for these continuous tokens, the video quality can be enhanced during reconstruction compared to conventional solutions. AR tokenizer can exploit the temporal causality between video frames by conditioning each frame's decoding on previous frames'pre-bottleneck features …

Translation: The system improves video clarity by using data from previous frames to predict the next one instead of rounding off details.

What this means for AI video generation at scale

For AI video generation tools, the tokenizer is the bottleneck nobody talks about. If the compression step degrades quality before the generative model even starts working, no amount of fine-tuning the generator recovers it. A tokenizer that preserves more signal at higher compression rates means the AI has better raw material to work with, which translates to sharper, more coherent output video.

For Nvidia, which sells the hardware that runs these workloads, a tokenizer that scales with compute is also a commercial argument: the more GPU time you spend training, the better the results get, with no ceiling in sight. The filing sits inside a busy category of new Big Tech patents targeting AI video infrastructure, where the compression layer is increasingly the competitive differentiator between systems that can handle long, high-resolution footage and those that can't.

Source: US 2026/0237209 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Nvidia patent news breaks.

There are more where this came from

We read the new patents from Big Tech, carmakers and more and send you the ones worth knowing. Plain English, free, every week.

The drawings · 14 sheets

14 drawing sheets from US 2026/0237209 A1 · click any drawing to enlarge

Image and video tokenizers, drawing sheet 1 from US 2026/0237209 A1
Sheet 1 Image and video tokenizers
Two-stage compression pipeline, drawing sheet 2 from US 2026/0237209 A1
Sheet 2 Two-stage compression pipeline
Convolution and quantization steps, drawing sheet 3 from US 2026/0237209 A1
Sheet 3 Convolution and quantization steps
Autoregressive versus standard tokenizers, drawing sheet 4 from US 2026/0237209 A1
Sheet 4 Autoregressive versus standard tokenizers
Autoregressive prediction steps, drawing sheet 5 from US 2026/0237209 A1
Sheet 5 Autoregressive prediction steps
Video generation and decoding, drawing sheet 6 from US 2026/0237209 A1
Sheet 6 Video generation and decoding
Comparison of attention and concatenation methods, drawing sheet 7 from US 2026/0237209 A1
Sheet 7 Comparison of attention and concatenation methods
Full and casual attention patterns, drawing sheet 8 from US 2026/0237209 A1
Sheet 8 Full and casual attention patterns
Show the other 6 sheets
Nvidia Patents a Two-Stage Video Compression System That Avoids Quality Degradation patent drawing, sheet 9
Sheet 9
Nvidia Patents a Two-Stage Video Compression System That Avoids Quality Degradation patent drawing, sheet 10
Sheet 10
Nvidia Patents a Two-Stage Video Compression System That Avoids Quality Degradation patent drawing, sheet 11
Sheet 11
Nvidia Patents a Two-Stage Video Compression System That Avoids Quality Degradation patent drawing, sheet 12
Sheet 12
Nvidia Patents a Two-Stage Video Compression System That Avoids Quality Degradation patent drawing, sheet 13
Sheet 13
Nvidia Patents a Two-Stage Video Compression System That Avoids Quality Degradation patent drawing, sheet 14
Sheet 14
Patent filing page

Watchlists this filing belongs to

All watchlists →