3D Hand Shape and Pose from Images in the Wild
This work addresses the challenge of accurate 3D hand modeling from unconstrained images, which is important for applications like human-computer interaction and augmented reality, but it is incremental as it builds on prior model-based and deep learning approaches.
The authors tackled the problem of predicting 3D hand shape and pose from RGB images in the wild using an end-to-end deep learning method, achieving state-of-the-art performance on standard benchmarks and producing geometrically valid reconstructions.
We present in this work the first end-to-end deep learning based method that predicts both 3D hand shape and pose from RGB images in the wild. Our network consists of the concatenation of a deep convolutional encoder, and a fixed model-based decoder. Given an input image, and optionally 2D joint detections obtained from an independent CNN, the encoder predicts a set of hand and view parameters. The decoder has two components: A pre-computed articulated mesh deformation hand model that generates a 3D mesh from the hand parameters, and a re-projection module controlled by the view parameters that projects the generated hand into the image domain. We show that using the shape and pose prior knowledge encoded in the hand model within a deep learning framework yields state-of-the-art performance in 3D pose prediction from images on standard benchmarks, and produces geometrically valid and plausible 3D reconstructions. Additionally, we show that training with weak supervision in the form of 2D joint annotations on datasets of images in the wild, in conjunction with full supervision in the form of 3D joint annotations on limited available datasets allows for good generalization to 3D shape and pose predictions on images in the wild.