论文标题
I2L-MESHNET：从单个RGB图像中进行精确3D人姿势和网格估计的图像到固件预测网络
I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image
论文作者
论文摘要
先前的大多数基于图像的3D人体姿势和网格估计方法从输入图像估算人网格模型的参数。但是，直接从输入图像中回归参数是一个高度非线性映射，因为它打破了输入图像中像素之间的空间关系。此外，它无法对预测不确定性进行建模，这可能会使培训更加困难。为了解决上述问题，我们提出了I2L-MESHNET，即图像到固件（线+像素）预测网络。提出的I2L-meshNET预测每个网格顶点坐标的1D热图上的每个液化可能性，而不是直接回归参数。我们的基于Lixel的1D热图保留了输入图像中的空间关系，并模拟了预测不确定性。我们证明了图像到固件预测的好处，并表明所提出的I2L-meshnet优于先前的方法。该代码公开可用https://github.com/mks0601/i2l-meshnet_release。
Most of the previous image-based 3D human pose and mesh estimation methods estimate parameters of the human mesh model from an input image. However, directly regressing the parameters from the input image is a highly non-linear mapping because it breaks the spatial relationship between pixels in the input image. In addition, it cannot model the prediction uncertainty, which can make training harder. To resolve the above issues, we propose I2L-MeshNet, an image-to-lixel (line+pixel) prediction network. The proposed I2L-MeshNet predicts the per-lixel likelihood on 1D heatmaps for each mesh vertex coordinate instead of directly regressing the parameters. Our lixel-based 1D heatmap preserves the spatial relationship in the input image and models the prediction uncertainty. We demonstrate the benefit of the image-to-lixel prediction and show that the proposed I2L-MeshNet outperforms previous methods. The code is publicly available https://github.com/mks0601/I2L-MeshNet_RELEASE.
