SketchDream: Sketch-based Text-To-3D Generation and Editing
ACM Transactions on Graphics · 19.07.2024 · 43 (4) · 1-13
DOI: 10.1145/3658120 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 19.07.2024. Verfasst von Feng-Lin Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Beijing Municipal Natural Science Foundation for Distinguished Young Scholars, Beijing Municipal Science and Technology Commission.
Abstract (Originalsprache)
Existing text-based 3D generation methods generate attractive results but lack detailed geometry control. Sketches, known for their conciseness and expressiveness, have contributed to intuitive 3D modeling but are confined to producing texture-less mesh models within predefined categories. Integrating sketch and text simultaneously for 3D generation promises enhanced control over geometry and appearance but faces challenges from 2D-to-3D translation ambiguity and multi-modal condition integration. Moreover, further editing of 3D models in arbitrary views will give users more freedom to customize their models. However, it is difficult to achieve high generation quality, preserve unedited regions, and manage proper interactions between shape components. To solve the above issues, we propose a text-driven 3D content generation and editing method, SketchDream, which supports NeRF generation from given hand-drawn sketches and achieves free-view sketch-based local editing. To tackle the 2D-to-3D ambiguity challenge, we introduce a sketch-based multi-view image generation diffusion model, which leverages depth guidance to establish spatial correspondence. A 3D ControlNet with a 3D attention module is utilized to control multi-view images and ensure their 3D consistency. To support local editing, we further propose a coarse-to-fine editing approach: the coarse phase analyzes component interactions and provides 3D masks to label edited regions, while the fine stage generates realistic results with refined details by local enhancement. Extensive experiments validate that our method generates higher-quality results compared with a combination of 2D ControlNet and image-to-3D generation techniques and achieves detailed control compared with existing diffusion-based 3D editing approaches.
Förderung
- National Natural Science Foundation of China
- Beijing Municipal Natural Science Foundation for Distinguished Young Scholars
- Beijing Municipal Science and Technology Commission
Zitieren
APA
Liu, F., Fu, H., Lai, Y., & Gao, L. (2024). SketchDream: Sketch-based Text-To-3D Generation and Editing. ACM Transactions on Graphics, 43(4), 1-13. https://doi.org/10.1145/3658120
Vancouver
Liu F, Fu H, Lai Y, Gao L. SketchDream: Sketch-based Text-To-3D Generation and Editing. ACM Transactions on Graphics. 2024;43(4):1-13. doi:10.1145/3658120
BibTeX
@article{Liu2024,
author = {Liu, Feng-Lin and Fu, Hongbo and Lai, Yu-Kun and Gao, Lin},
title = {SketchDream: Sketch-based Text-To-3D Generation and Editing},
journal = {ACM Transactions on Graphics},
year = {2024},
volume = {43},
number = {4},
pages = {1--13},
doi = {10.1145/3658120}
}
EUVIMED