I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modeling
This work aims to improve the accuracy and fidelity of 3D hand reconstruction from images for applications in human-computer interaction and virtual reality, addressing limitations of current methods for these domains.
This paper addresses the challenge of reconstructing high-precision and high-fidelity 3D human hands from color images, which is crucial for virtual reality and human-computer interaction. The authors propose I2UV-HandNet, which uses a novel UV-based 3D hand shape representation and an AffineNet for UV position map prediction, followed by an SRNet for super-resolution, achieving state-of-the-art performance on several benchmarks.
Reconstructing a high-precision and high-fidelity 3D human hand from a color image plays a central role in replicating a realistic virtual hand in human-computer interaction and virtual reality applications. The results of current methods are lacking in accuracy and fidelity due to various hand poses and severe occlusions. In this study, we propose an I2UV-HandNet model for accurate hand pose and shape estimation as well as 3D hand super-resolution reconstruction. Specifically, we present the first UV-based 3D hand shape representation. To recover a 3D hand mesh from an RGB image, we design an AffineNet to predict a UV position map from the input in an image-to-image translation fashion. To obtain a higher fidelity shape, we exploit an additional SRNet to transform the low-resolution UV map outputted by AffineNet into a high-resolution one. For the first time, we demonstrate the characterization capability of the UV-based hand shape representation. Our experiments show that the proposed method achieves state-of-the-art performance on several challenging benchmarks.