2020 CVPR CVPR 2020

A Neural Rendering Framework for Free-Viewpoint Relighting

Abstract

We present a novel Relightable Neural Renderer (RNR) for simultaneous view synthesis and relighting using multi-view image inputs. Existing neural rendering (NR) does not explicitly model the physical rendering process and hence has limited capabilities on relighting. RNR instead models image formation in terms of environment lighting, object intrinsic attributes, and light transport function (LTF), each corresponding to a learnable component. In particular, the incorporation of a physically based rendering process not only enables relighting but also improves the quality of view synthesis. Comprehensive experiments on synthetic and real data show that RNR provides a practical and effective solution for conducting free-viewpoint relighting.

🌉 Interdisciplinary Bridge — Computer Science and Computer Vision and Deep Learning
🧭 Keyword Pioneer — physically based rendering
🐣 Hot Topic Early Bird — neural rendering
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Interdisciplinary, Machine Learning, Mathematics & Optimization, Natural Language Processing, Robotics, Speech & Audio