HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation

Xin Huang, Ruizhi Shao, Qi Zhang, Hongwen Zhang, Ying Feng, Yebin Liu, Qing Wang

Keywords: diffusion model, 3D human

Abstract: Recent text-to-3D methods have marked significant progress in 3D human generation. However, these methods struggle with high-quality generation, resulting in smooth geometry and cartoon-like appearances. In this paper, we found that by fine-tuning the text-to-image diffusion model with normal maps, it can be adapted to a text-to-normal diffusion model, while preserving part of the generation priors learned from large-scale datasets. Therefore, we propose HumanNorm, a novel approach for high-quality and realistic 3D human generation by integrating normal maps into diffusion models. We employ two integration strategies and propose a normal-adapted diffusion model as well as a normal-aligned diffusion model. The normal-adapted diffusion model can generate high-fidelity normal maps corresponding to prompts with view-dependent text. The normal-aligned diffusion model learns to generate color images aligned with the normal maps, thereby transforming physical geometry details into realistic appearance. Leveraging the proposed normal diffusion model, we devise a progressive geometry generation strategy and coarse-to-fine texture generation strategy to enhance the efficiency and robustness of 3D human generation. Comprehensive experiments substantiate our method's ability to generate 3D humans with intricate geometry and realistic appearances, significantly outperforming existing text-to-3D methods in both geometry and texture quality.

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 3422