Locally Attentional SDF Diffusion for Controllable 3D Shape Generation
ACM Transactions on Graphics · 2023-08 · 42 (4) · 1-13
DOI: 10.1145/3592103 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 26.07.2023. Verfasst von Xin-Yang Zheng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 129-mal zitiert (Crossref) und nennt 92 Literaturangaben.
Abstract (Originalsprache)
Although the recent rapid evolution of 3D generative neural networks greatly improves 3D shape generation, it is still not convenient for ordinary users to create 3D shapes and control the local geometry of generated shapes. To address these challenges, we propose a diffusion-based 3D generation framework --- locally attentional SDF diffusion , to model plausible 3D shapes, via 2D sketch image input. Our method is built on a two-stage diffusion model. The first stage, named occupancy-diffusion , aims to generate a low-resolution occupancy field to approximate the shape shell. The second stage, named SDF-diffusion , synthesizes a high-resolution signed distance field within the occupied voxels determined by the first stage to extract fine geometry. Our model is empowered by a novel view-aware local attention mechanism for image-conditioned shape generation, which takes advantage of 2D image patch features to guide 3D voxel feature learning, greatly improving local controllability and model generalizability. Through extensive experiments in sketch-conditioned and category-conditioned 3D shape generation tasks, we validate and demonstrate the ability of our method to provide plausible and diverse 3D shapes, as well as its superior controllability and generalizability over existing work.
Zitieren
APA
Zheng, X., Pan, H., Wang, P., Tong, X., Liu, Y., & Shum, H. (2023). Locally Attentional SDF Diffusion for Controllable 3D Shape Generation. ACM Transactions on Graphics, 42(4), 1-13. https://doi.org/10.1145/3592103
Vancouver
Zheng X, Pan H, Wang P, Tong X, Liu Y, Shum H. Locally Attentional SDF Diffusion for Controllable 3D Shape Generation. ACM Transactions on Graphics. 2023;42(4):1-13. doi:10.1145/3592103
BibTeX
@article{Zheng2023,
author = {Zheng, Xin-Yang and Pan, Hao and Wang, Peng-Shuai and Tong, Xin and Liu, Yang and Shum, Heung-Yeung},
title = {Locally Attentional SDF Diffusion for Controllable 3D Shape Generation},
journal = {ACM Transactions on Graphics},
year = {2023},
volume = {42},
number = {4},
pages = {1--13},
doi = {10.1145/3592103}
}
EUVIMED