# \#meta-ai

**URL:** https://scanalyst.fourmilab.ch/tag/meta-ai/3692.md

[Latest](https://scanalyst.fourmilab.ch/latest.md) · [Categories](https://scanalyst.fourmilab.ch/categories.md) · [Tags](https://scanalyst.fourmilab.ch/tags.md)

---

## [Meta AI Announces “Make-A-Video3D”—Text or Image to Dynamic 3D Video](https://scanalyst.fourmilab.ch/t/meta-ai-announces-make-a-video3d-text-or-image-to-dynamic-3d-video/2672)

<div class="topic-metadata">

**Author:** [@johnwalker](https://scanalyst.fourmilab.ch/u/johnwalker)\
**Replies:** 0\
**Last updated:** [28 January 2023 14:35 UTC](https://scanalyst.fourmilab.ch/t/meta-ai-announces-make-a-video3d-text-or-image-to-dynamic-3d-video/2672 "2023-01-28T14:35:31Z")

</div>

In a paper posted to arXiV on 2023-01-26, “Text-To-4D Dynamic Scene Generation” (full text \[PDF\]), Meta AI researchers describe a system, MAV3D (“Make-A-Video3D”) which creates animated three-dimensional videos from text…