Monocular 3D reconstruction of deformable objects, such as human body parts, has been typically approached by predicting parameters of heavyweight linear models. In this paper, we demonstrate an alternative solution that is based on the idea of encoding images into a latent non-linear representation of meshes. The prior on 3D hand shapes is learned by training an autoencoder with intrinsic graph convolutions performed in the spectral domain. The pre-trained decoder acts as a non-linear statistical deformable model. The latent parameters that reconstruct the shape and articulated pose of hands in the image are predicted using an image encoder. We show that our system reconstructs plausible meshes and operates in real-time. We evaluate the quality of the mesh reconstructions produced by the decoder on a new dataset and show latent space interpolation results. Our code, data, and models will be made publicly available.

Figure 1: We propose an approach for end-to-end neural network training with mesh supervision that is obtained through an automated data collection method. We process a large collection of YouTube videos and analyze them with 2D hand keypoint detector followed by parametric model fitting (right side). The fitting results are used as a supervisory signal ('mesh loss') for a feed-forward network with a mesh convolutional decoder tasked with recovering a 3D hand mesh at its output (left side).

No abstract