4D reconstruction and rendering of human activities is critical for immersive VR/AR experience.Recent advances still fail to recover fine geometry and texture results with the level of detail present in the input images from sparse multi-view RGB cameras. In this paper, we propose NeuralHumanFVV, a real-time neural human performance capture and rendering system to generate both high-quality geometry and photo-realistic texture of human activities in arbitrary novel views. We propose a neural geometry generation scheme with a hierarchical sampling strategy for real-time implicit geometry inference, as well as a novel neural blending scheme to generate high resolution (e.g., 1k) and photo-realistic texture results in the novel views. Furthermore, we adopt neural normal blending to enhance geometry details and formulate our neural geometry and texture rendering into a multi-task learning framework. Extensive experiments demonstrate the effectiveness of our approach to achieve high-quality geometry and photo-realistic free view-point reconstruction for challenging human performances.
@article{arxiv.2103.07700,
title = {NeuralHumanFVV: Real-Time Neural Volumetric Human Performance Rendering using RGB Cameras},
author = {Xin Suo and Yuheng Jiang and Pei Lin and Yingliang Zhang and Kaiwen Guo and Minye Wu and Lan Xu},
journal= {arXiv preprint arXiv:2103.07700},
year = {2021}
}