HandAugment: A Simple Data Augmentation Method for Depth-Based 3D Hand Pose Estimation

Hand pose estimation from 3D depth images, has been explored widely using various kinds of techniques in the field of computer vision. Though, deep learning based method improve the performance greatly recently, however, this problem still remains unsolved due to lack of large datasets, like ImageNet or effective data synthesis methods. In this paper, we propose HandAugment, a method to synthesize image data to augment the training process of the neural networks. Our method has two main parts: First, We propose a scheme of two-stage neural networks. This scheme can make the neural networks focus on the hand regions and thus to improve the performance. Second, we introduce a simple and effective method to synthesize data by combining real and synthetic image together in the image space. Finally, we show that our method achieves the first place in the task of depth-based 3D hand pose estimation in HANDS 2019 challenge.

HandAugment: A Simple Data Augmentation for HANDS19 Challenge Task 1 -- Depth-Based 3D Hand Pose Estimation

Hand pose estimation from 3D depth images, has been explored widely using various kinds of techniques in the field of computer vision. However, this problem still remain unsolved. In this paper we present HandAugment, a simple data augmentation for depth-based 3D hand pose estimation. HandAugment consists of two stages of neural networks. The first stage of neural network is used to extract hand patches and estimate the initial hand poses from the depth images in an iteration fashion. This step can help filter out more outlier patches away (e.g., arms and backgrounds). Then the extracted patches and initial hand poses are further feed into the neural network of the second stage to get the final hand poses. This strategy of two stages greatly improves the accuracy of hands pose estimation. Finally, our method achieves the first place in the task of depth-based 3D hand pose estimation in HANDS19 challenge.

End-To-End Face Detection and Recognition

Plenty of face detection and recognition methods have been proposed and got delightful results in decades. Common face recognition pipeline consists of: 1) face detection, 2) face alignment, 3) feature extraction, 4) similarity calculation, which are separated and independent from each other. The separated face analyzing stages lead the model redundant calculation and are hard for end-to-end training. In this paper, we proposed a novel end-to-end trainable convolutional network framework for face detection and recognition, in which a geometric transformation matrix was directly learned to align the faces, instead of predicting the facial landmarks. In training stage, our single CNN model is supervised only by face bounding boxes and personal identities, which are publicly available from WIDER FACE \cite{Yang2016} dataset and CASIA-WebFace \cite{Yi2014} dataset. Tested on Face Detection Dataset and Benchmark (FDDB) \cite{Jain2010} dataset and Labeled Face in the Wild (LFW) \cite{Huang2007} dataset, we have achieved 89.24\% recall for face detection task and 98.63\% verification accuracy for face recognition task simultaneously, which are comparable to state-of-the-art results.