EUVIMEDEUVIMED entdecken
Crossref

IT3D: Improved Text-to-3D Generation with Explicit View Synthesis

Yiwen Chen, Chi Zhang, Xiaofeng Yang, Zhongang Cai, Gang Yu, Lei Yang, Guosheng Lin

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (2) · 1237-1244

DOI: 10.1609/aaai.v38i2.27886 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Yiwen Chen und 6 weiteren Autor:innen. Die Arbeit wurde bisher 47-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent strides in Text-to-3D techniques have been propelled by distilling knowledge from powerful large text-to-image diffusion models (LDMs). Nonetheless, existing Text-to-3D approaches often grapple with challenges such as over-saturation, inadequate detailing, and unrealistic outputs. This study presents a novel strategy that leverages explicitly synthesized multi-view images to address these issues. Our approach involves the utilization of image-to-image pipelines, empowered by LDMs, to generate posed high-quality images based on the renderings of coarse 3D models. Although the generated images mostly alleviate the aforementioned issues, challenges such as view inconsistency and significant content variance persist due to the inherent generative nature of large diffusion models, posing extensive difficulties in leveraging these images effectively. To overcome this hurdle, we advocate integrating a discriminator alongside a novel Diffusion-GAN dual training strategy to guide the training of 3D models. For the incorporated discriminator, the synthesized multi-view images are considered real data, while the renderings of the optimized 3D models function as fake data. We conduct a comprehensive set of experiments that demonstrate the effectiveness of our method over baseline approaches.

Zitieren

APA

Chen, Y., Zhang, C., Yang, X., Cai, Z., Yu, G., Yang, L., & Lin, G. (2024). IT3D: Improved Text-to-3D Generation with Explicit View Synthesis. Proceedings of the AAAI Conference on Artificial Intelligence, 38(2), 1237-1244. https://doi.org/10.1609/aaai.v38i2.27886

Vancouver

Chen Y, Zhang C, Yang X, Cai Z, Yu G, Yang L, et al. IT3D: Improved Text-to-3D Generation with Explicit View Synthesis. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(2):1237-1244. doi:10.1609/aaai.v38i2.27886

BibTeX
@article{Chen2024,
  author = {Chen, Yiwen and Zhang, Chi and Yang, Xiaofeng and Cai, Zhongang and Yu, Gang and Yang, Lei and Lin, Guosheng},
  title = {IT3D: Improved Text-to-3D Generation with Explicit View Synthesis},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {2},
  pages = {1237--1244},
  doi = {10.1609/aaai.v38i2.27886}
}
Kostenlos starten →