AI Paper Atlas

Research map / Video / Video generation

Phenaki: Variable Length Video Generation from Open Domain Textual Descriptions

Ruben Villegas, Mohammad Babaeizadeh, Pieter-Jan Kindermans, Hernan Moraldo, Han Zhang, Mohammad Taghi Saffar, Santiago Castro, Julius Kunze, Dumitru Erhan

ICLR 2023 · Video › Video generation · approach: Compositional text-to-video diffusion · 79 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train with more image data rather than video-only data (ablation)Phenaki · Text-to-videoCLIP: 0.298 -> 0.303Improved
train with more image data rather than video-only data (ablation)Phenaki · Text-to-videoFVD: 168.9 -> 198.4Hurt
train with image data rather than video-only data (ablation)Phenaki · Text-to-imageFID: 53.9 -> 29.4Improved
increase image data from 20% to 50% (ablation)Phenaki · Text-to-videoFVD: 198.4 -> 239.7Hurt
use C-ViViT temporal-spatial video encoding instead of per-frame ViT VQ-GANVideo quantization · Moments-in-TimeFVD: 166.6 -> 65.78Improved
use C-ViViT temporal-spatial video encoding instead of per-frame ViT VQ-GANVideo quantization · Moments-in-TimeNumber of Tokens: 2560 -> 1536Improved
use C-ViViT instead of per-frame ViT VQ-GANVideo quantization · Moments-in-TimeFID: 3.4 -> 4.5Hurt
use Phenaki for video prediction rather than the strongest listed baselineVideo prediction · Kinetics-600FVD: 16.2 ± 0.34 -> 36.4 ± 0.19Hurt
use Phenaki for video prediction rather than the strongest listed baselineVideo prediction · BAIRFVD: 84.2 -> 97.0Hurt
use zero-shot Phenaki instead of NUWAText-to-video generation · Kinetics-400FID Video: 7.05 -> 3.84Improved

Later papers that compared with this method

4 later accepted papers report Phenaki as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy