PIFuHD：用于高分辨率三维人体数字化的多级像素对齐隐式函数
PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization
摘要：
基于图像的3D人体形状估计的最新进展是由深度神经网络提供的表示能力的显著改进驱动的。虽然目前的方法已经证明了在现实世界中的设置的潜力，他们仍然无法产生重建的详细程度往往存在于输入图像。我们认为，这种限制主要源于两个相互冲突的要求;准确的预测需要大的背景，但精确的预测需要高分辨率。由于当前硬件中的存储器限制，先前的方法倾向于将低分辨率图像作为输入以覆盖大空间上下文，并且因此产生不太精确（或低分辨率）的3D估计。我们通过制定一个端到端可训练的多层架构来解决这个限制。粗层次以较低的分辨率观察整个图像，并专注于整体推理。这提供了通过观察更高分辨率的图像来估计高度详细的几何形状的精细水平的上下文。我们证明，我们的方法显着优于现有的最先进的技术，通过充分利用1 k分辨率的输入图像的单图像人体形状重建。
英文摘要：
Recent advances in image-based 3D human shape estimation have been driven by the significant improvement in representation power afforded by deep neural networks. Although current approaches have demonstrated the potential in real world settings, they still fail to produce reconstructions with the level of detail often present in the input images. We argue that this limitation stems primarily form two conflicting requirements; accurate predictions require large context, but precise predictions require high resolution. Due to memory limitations in current hardware, previous approaches tend to take low resolution images as input to cover large spatial context, and produce less precise (or low resolution) 3D estimates as a result. We address this limitation by formulating a multi-level architecture that is end-to-end trainable. A coarse level observes the whole image at lower resolution and focuses on holistic reasoning. This provides context to an fine level which estimates highly detailed geometry by observing higher-resolution images. We demonstrate that our approach significantly outperforms existing state-of-the-art techniques on single image human shape reconstruction by fully leveraging 1k-resolution input images.
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。
