English

Free-Viewpoint RGB-D Human Performance Capture and Rendering

Computer Vision and Pattern Recognition 2022-08-03 v4 Graphics

Abstract

Capturing and faithfully rendering photo-realistic humans from novel views is a fundamental problem for AR/VR applications. While prior work has shown impressive performance capture results in laboratory settings, it is non-trivial to achieve casual free-viewpoint human capture and rendering for unseen identities with high fidelity, especially for facial expressions, hands, and clothes. To tackle these challenges we introduce a novel view synthesis framework that generates realistic renders from unseen views of any human captured from a single-view and sparse RGB-D sensor, similar to a low-cost depth camera, and without actor-specific models. We propose an architecture to create dense feature maps in novel views obtained by sphere-based neural rendering, and create complete renders using a global context inpainting model. Additionally, an enhancer network leverages the overall fidelity, even in occluded areas from the original view, producing crisp renders with fine details. We show that our method generates high-quality novel views of synthetic and real human actors given a single-stream, sparse RGB-D input. It generalizes to unseen identities, and new poses and faithfully reconstructs facial expressions. Our approach outperforms prior view synthesis methods and is robust to different levels of depth sparsity.

Keywords

Cite

@article{arxiv.2112.13889,
  title  = {Free-Viewpoint RGB-D Human Performance Capture and Rendering},
  author = {Phong Nguyen-Ha and Nikolaos Sarafianos and Christoph Lassner and Janne Heikkila and Tony Tung},
  journal= {arXiv preprint arXiv:2112.13889},
  year   = {2022}
}

Comments

Accepted at ECCV 2022, Project page: https://www.phongnhhn.info/HVS_Net/index.html

R2 v1 2026-06-24T08:33:05.242Z