Pixel-aligned implicit models, such as PIFu, PIFuHD, and ICON, are used for single-view clothed human reconstruction. These models need to be trained using a sampling training scheme. Existing sampling training schemes either fail to capture thin surfaces (e.g. ears, fingers) or cause noisy artefacts in reconstructed meshes. To address these problems, we introduce Fine Structured-Aware Sampling (FSS), a new sampling training scheme to train pixel-aligned implicit models for single-view human reconstruction. FSS resolves the aforementioned problems by proactively adapting to the thickness and complexity of surfaces. In addition, unlike existing sampling training schemes, FSS shows how normals of sample points can be capitalized in the training process to improve results. Lastly, to further improve the training process, FSS proposes a mesh thickness loss signal for pixel-aligned implicit models. It becomes computationally feasible to introduce this loss once a slight reworking of the pixel-aligned implicit function framework is carried out. Our results show that our methods significantly outperform SOTA methods qualitatively and quantitatively. Our code is publicly available at https://github.com/kcyt/FSS.

翻译：像素对齐隐式模型（如PIFu、PIFuHD和ICON）被用于单视角穿衣人体重建。这类模型需通过采样训练方案进行训练。现有采样训练方案要么难以捕捉薄表面（如耳朵、手指），要么会导致重建网格产生噪声伪影。为解决这些问题，我们提出精细结构感知采样（FSS）——一种面向单视角人体重建的像素对齐隐式模型的新型采样训练方案。FSS通过主动适应表面的厚度与复杂度来解决上述问题。此外，与现有采样训练方案不同，FSS展示了如何在训练过程中利用采样点的法向量以提升重建效果。最后，为进一步优化训练过程，FSS提出了一种面向像素对齐隐式模型的网格厚度损失信号。通过对像素对齐隐式函数框架进行轻微重构，该损失的引入在计算上成为可行。实验结果表明，我们的方法在定性和定量上均显著优于当前最先进方法。我们的代码已公开于https://github.com/kcyt/FSS。