Real-time 3D human reconstruction and rendering system from a single RGB camera

Yang, Yuanwang, Feng, Qiao, Lai, Yu-Kun ORCID: https://orcid.org/0000-0002-2094-5680 and Li, Kun 2024. Real-time 3D human reconstruction and rendering system from a single RGB camera. Presented at: SA '24: SIGGRAPH Asia 2024 Technical Communications, Tokyo, Japan, 3-6 December 2024. Published in: Igarashi, Takeo and Hu, Ruizhen eds. SA '24: SIGGRAPH Asia 2024 Technical Communications. New York: ACM, 10.1145/3681758.3697993

Preview

PDF - Accepted Post-Print Version Download (1MB) | Preview

Abstract

Transforming 2D human images into 3D appearance is essential for immersive communication. In this paper, we introduce a low-cost real-time 3D human reconstruction and rendering system with a single RGB camera at 28+ FPS, which guarantees both real-time computing speed and realistic rendering results. We use WebRTC to transmit captured images over the Internet for low-latency remote communication. In addition, we design a lighting-robust rendering approach to enhance the lighting perception and generalization ability of the model. Experimental results show that our system achieves high-quality real-time 3D human reconstruction and rendering for different persons wearing various clothes, even with challenging poses. Our system makes use of only a common USB webcam and a consumer-level GPU with real-time performance and high-fidelity results, which provides a consumer-accessible immersive telepresence solution.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	ACM
ISBN:	9798400711404
Date of First Compliant Deposit:	9 December 2024
Date of Acceptance:	24 September 2024
Last Modified:	09 Dec 2024 13:15
URI:	https://orca.cardiff.ac.uk/id/eprint/174357

Actions (repository staff only)

Edit Item