RenderIH: A Large-scale Synthetic Dataset for 3D Interacting Hand Pose Estimation

TL;DR

RenderIH is a large-scale synthetic dataset with diverse, photo-realistic images of interacting hands, designed to improve 3D hand pose estimation accuracy through a new pose optimization algorithm and a transformer-based network.

Contribution

The paper introduces RenderIH, a large-scale synthetic dataset with diverse annotations, and proposes a novel pose optimization algorithm and a transformer-based network for enhanced 3D hand pose estimation.

Findings

Pretraining on RenderIH reduces pose estimation error from 6.76mm to 5.79mm.

RenderIH improves the accuracy of hand pose estimation methods.

TransHand surpasses contemporary methods in interacting hand pose estimation.

Abstract

The current interacting hand (IH) datasets are relatively simplistic in terms of background and texture, with hand joints being annotated by a machine annotator, which may result in inaccuracies, and the diversity of pose distribution is limited. However, the variability of background, pose distribution, and texture can greatly influence the generalization ability. Therefore, we present a large-scale synthetic dataset RenderIH for interacting hands with accurate and diverse pose annotations. The dataset contains 1M photo-realistic images with varied backgrounds, perspectives, and hand textures. To generate natural and diverse interacting poses, we propose a new pose optimization algorithm. Additionally, for better pose estimation accuracy, we introduce a transformer-based pose estimation network, TransHand, to leverage the correlation between interacting hands and verify the effectiveness of RenderIH in improving results. Our dataset is model-agnostic and can improve more accuracy of any hand pose estimation method in comparison to other real or synthetic datasets. Experiments have shown that pretraining on our synthetic data can significantly decrease the error from 6.76mm to 5.79mm, and our Transhand surpasses contemporary methods. Our dataset and code are available at https://github.com/adwardlee/RenderIH.