用SMPL法线图实现单图真人三维重建，效果超越现有方法
SMPL Normal Map Is All You Need for Single-view Textured Human Reconstruction
- 引入SMPL法线图作为几何先验，指导三维重建
- 无需扩散模型，一次前向传播完成重建，速度快且准确
- 适合需要快速高质量人体建模的场景，如虚拟试衣
单视图纹理人体重建旨在仅输入一张2D图像即可重建穿衣服的3D数字人。现有方法包括前馈型方法（受限于稀缺的3D人体数据）和基于扩散的方法（易产生错误的2D幻觉）。为此，本文提出一种新型的SMPL法线图驱动3D人体重建框架SEHR，结合预训练的大规模3D重建模型与人体几何先验。SEHR在一次前向传播中完成单视图人体重建，无需预设扩散模型。具体包含两个关键组件：SMPL法线图引导（SNMG）和SMPL法线图约束（SNMC）。SNMG通过辅助网络引入SMPL法线图，提升身体形状引导精度；SNMC通过约束模型预测额外的SMPL法线高斯分布，增强不可见部位的重建质量。在两个基准数据集上的大量实验表明，SEHR优于现有最先进方法。
原文摘要 · Abstract (English)
Single-view textured human reconstruction aims to reconstruct a clothed 3D digital human by inputting a monocular 2D image. Existing approaches include feed-forward methods, limited by scarce 3D human data, and diffusion-based methods, prone to erroneous 2D hallucinations. To address these issues, we propose a novel SMPL normal map Equipped 3D Human Reconstruction (SEHR) framework, integrating a pretrained large 3D reconstruction model with human geometry prior. SEHR performs single-view human reconstruction without using a preset diffusion model in one forward propagation. Concretely, SEHR consists of two key components: SMPL Normal Map Guidance (SNMG) and SMPL Normal Map Constraint (SNMC). SNMG incorporates SMPL normal maps into an auxiliary network to provide improved body shape guidance. SNMC enhances invisible body parts by constraining the model to predict an extra SMPL normal Gaussians. Extensive experiments on two benchmark datasets demonstrate that SEHR outperforms existing state-of-the-art methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。