Paper Image

Progressively editing 3D content from text

Published on:

18 October 2023

Primary Category:

Computer Vision and Pattern Recognition

Paper Authors:

Xinhua Cheng,

Tianyu Yang,

Jianan Wang,

Yu Li,

Lei Zhang,

Jian Zhang,

Li Yuan

Bullets

Key Details

Proposes Progressive3D framework for precise text-to-3D generation

Decomposes complex prompts into progressive local editing steps

Constraints maintain unchanged regions and initialize empty space

Overlapped semantics suppression focuses optimization

AI generated summary

Progressively editing 3D content from text

This paper proposes a framework to generate precise 3D content from complex text prompts, by progressively making local edits in multiple steps. It decomposes a difficult prompt into easier steps.

Answers from this paper

Comments

No comments yet, be the first to start the conversation...

Sign up to comment on this paper

Sign Up