Methods › Computer Vision › Generative Models › TrIVD-GAN

TrIVD-GAN

1 paper tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

TrIVD-GAN, or Transformation-based & TrIple Video Discriminator GAN, is a type of generative adversarial network for video generation that builds upon DVD-GAN. Improvements include a novel transformation-based recurrent unit (the TSRU) that makes the generator more expressive, and an improved discriminator architecture.

In contrast with DVD-GAN, TrIVD-GAN has an alternative split for the roles of the discriminators, with 𝒟_S judging per-frame global structure, while 𝒟_T critiques local spatiotemporal structure. This is achieved by downsampling the k randomly sampled frames fed to 𝒟_S by a factor s, and cropping T ×H/s ×W/s clips inside the high resolution video fed to 𝒟_T, where T, H, W, C correspond to time, height, width and channel dimension of the input. This further reduces the number of pixels to process per video, from k ×H ×W + T ×H/s ×W/s to (k + T) ×H/s ×W/s.

Source: Transformation-based Adversarial Video Prediction on...

Papers archive 2025-07-28

1 shown of 1, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

3 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Prediction1
Video Generation1
Video Prediction1

Usage over time archive 2025-07-28

Papers per year tagged with TrIVD-GAN: 2020 to 2020, peak 1 1 0 2020: 1 paper 2020
Papers per year the archive tags with this method, by the paper's archive date (1 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Generative Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections