Chirpy3D: Continuous Part Latents for Creative 3D Bird Generation - podcast episode cover

Chirpy3D: Continuous Part Latents for Creative 3D Bird Generation

Jan 10, 2025•24 min•Ep. 358
--:--
--:--
Download Metacast podcast app
Listen to this episode in Metacast mobile app
Don't just listen to podcasts. Learn from them with transcripts, summaries, and chapters for every episode. Skim, search, and bookmark insights. Learn more

Episode description

🤗 Upvotes: 10 | cs.CV, cs.GR

Authors:
Kam Woh Ng, Jing Yang, Jia Wei Sii, Jiankang Deng, Chee Seng Chan, Yi-Zhe Song, Tao Xiang, Xiatian Zhu

Title:
Chirpy3D: Continuous Part Latents for Creative 3D Bird Generation

Arxiv:
http://arxiv.org/abs/2501.04144v1

Abstract:
In this paper, we push the boundaries of fine-grained 3D generation into truly creative territory. Current methods either lack intricate details or simply mimic existing objects -- we enable both. By lifting 2D fine-grained understanding into 3D through multi-view diffusion and modeling part latents as continuous distributions, we unlock the ability to generate entirely new, yet plausible parts through interpolation and sampling. A self-supervised feature consistency loss further ensures stable generation of these unseen parts. The result is the first system capable of creating novel 3D objects with species-specific details that transcend existing examples. While we demonstrate our approach on birds, the underlying framework extends beyond things that can chirp! Code will be released at https://github.com/kamwoh/chirpy3d.

For the best experience, listen in Metacast app for iOS or Android