PaintHuman：通过去噪分数蒸馏实现高保真文本到三维人体纹理生成
PaintHuman: Towards High-fidelity Text-to-3D Human Texturing via Denoised Score Distillation
AI总结：
PaintHuman提出去噪分数蒸馏（DSD）和深度图几何引导，解决SDS梯度不准确问题，实现高保真文本到三维人体纹理生成。
摘要：
近年来，零样本文本到三维人体生成取得了突破性进展，这些方法利用人体模型先验（如SMPL）或结合预训练文本到图像扩散模型的分数蒸馏采样（SDS）。然而，在弱扩散引导下，SDS可能提供不准确的梯度方向，因为它倾向于产生过度平滑的结果，并生成与详细网格几何不一致的人体纹理。因此，直接利用现有策略进行高保真文本到三维人体纹理生成是具有挑战性的。在这项工作中，我们提出了一种名为PaintHuman的模型，从两个方面解决这些挑战。我们首先提出了一种新颖的分数函数，即去噪分数蒸馏（DSD），它通过引入负梯度分量来直接修改SDS，以迭代校正梯度方向并生成高质量纹理。此外，我们使用深度图作为几何引导，以确保纹理与人体网格表面语义对齐。为了保证渲染结果的质量，我们采用几何感知网络来预测表面材质并渲染逼真的人体纹理。与最先进方法相比的大量实验验证了我们方法的有效性。
英文摘要：
Recent advances in zero-shot text-to-3D human generation, which employ the human model prior (eg, SMPL) or Score Distillation Sampling (SDS) with pre-trained text-to-image diffusion models, have been groundbreaking. However, SDS may provide inaccurate gradient directions under the weak diffusion guidance, as it tends to produce over-smoothed results and generate body textures that are inconsistent with the detailed mesh geometry. Therefore, directly leverage existing strategies for high-fidelity text-to-3D human texturing is challenging. In this work, we propose a model called PaintHuman to addresses the challenges from two aspects. We first propose a novel score function, Denoised Score Distillation (DSD), which directly modifies the SDS by introducing negative gradient components to iteratively correct the gradient direction and generate high-quality textures. In addition, we use the depth map as a geometric guidance to ensure the texture is semantically aligned to human mesh surfaces. To guarantee the quality of rendered results, we employ geometry-aware networks to predict surface materials and render realistic human textures. Extensive experiments, benchmarked against state-of-the-art methods, validate the efficacy of our approach.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
