Episode

Generating 3D Animals with YouDream

Podcast
Data Skeptic
Published
Jul 23, 2024
Duration seconds
3609
Processing state
failed
Canonical source
https://dataskeptic.com/blog/episodes/2024/generating-3d-animals
Audio
https://pscrb.fm/rss/p/mgln.ai/e/35/traffic.libsyn.com/secure/dataskeptic/generating-3d-animals.mp3?dest-id=201630
JSON
/v1/public/podcasts/data-skeptic/episodes/generating-3d-animals-with-youdream
Markdown
/podcast/data-skeptic/generating-3d-animals-with-youdream.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/data-skeptic/episodes/generating-3d-animals-with-youdream/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/data-skeptic/generating-3d-animals-with-youdream.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

Generative AI can struggle to create realistic animals and 2D representations often have mistakes like extra limbs and tails. If 2D wasn't hard enough, there are researchers working on generative 3D models. 3D models present an extra challenge because there is paucity of training datasets.In this episode, PhD students Sandeep and Oindrila walked us through their work on creating 3D animals using 2D data. Join us to learn about their pipelines, quality control, tie in with iNaturalist, and how this tech could streamline FX pipelines.