Google patents method for generating video sequences with neural networks
Google describes a technique for creating time-based data sequences, such as video frames, by starting with random noise and refining it step by step. The system uses a neural network to clean up each segment of the sequence while keeping track of previous segments to ensure the final output flows smoothly.
In the filing’s own words
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output temporal sequence of data elements conditioned on an input. In one aspect, a method comprises: obtaining the input, wherein the input comprises a noise input comprising a respective latent representation for each of a plurality of segments of the temporal sequence; updating, for each segment, the latent representation for the segment using a latent denoising neural network, the updating comprising, for each segment other than the first segment: obtaining a memory vector representing one or more hidden states generated by the latent denoising neural network when updating the latent representations for one or more preceding segments; updating the latent representation for the segment at each of a plurality of iterations; and generating the output temporal sequence of data elements by processing the latent representations for the plurality of segments.
What exactly they claim (claim 1)
1. A computer-implemented method of generating an output temporal sequence of data elements conditioned on an input, the method comprising: obtaining the input, wherein the input comprises a noise input comprising a respective latent representation for each of a plurality of segments of the temporal sequence, each segment comprising one or more data elements of the output temporal sequence of data elements; updating, for each segment, the latent representation for the segment using a latent denoising neural network, wherein the latent denoising neural network is configured to autoregressively update the latent representations for each segment, the updating comprising, for each segment other than the first segment: obtaining a memory vector representing one or more hidden states generated by the latent denoising neural network when updating the latent representations for one or more preceding segments; updating the latent representation for the segment at each of a plurality of iterations, wherein the updating comprises, at each iteration: processing an intermediate input for the iteration comprising the latent representation and the memory vector to generate a denoising output; and updating the latent representation using the denoising output for the iteration; and generating the output temporal sequence of data elements by processing the latent representations for the plurality of segments using a decoder neural network.
Facts
- Company
- Google (Google LLC)
- Official title
- Generating temporal sequences using diffusion transformer neural networks
- Patent number
- US12743465B2
- Application number
- 19216518
- Filed
- May 22, 2025
- Granted
- Sep 22, 2026
- Inventors
- 7
- Claims
- 20
Classified under
G06F 16/743 Physics & computingG06N 3/09 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.