A Light Stage on Every Desk

TL;DR

This paper introduces a method to perform realistic face relighting using standard monitors, enabling synthetic relighting of faces with arbitrary illumination conditions without specialized equipment.

Contribution

It demonstrates how to acquire and use monitor-based lighting data for face relighting, eliminating the need for expensive, room-scale light stage setups.

Findings

Produces realistic relighting results

Operates with images of users watching standard content

Uses deep learning to predict relit images

Abstract

Every time you sit in front of a TV or monitor, your face is actively illuminated by time-varying patterns of light. This paper proposes to use this time-varying illumination for synthetic relighting of your face with any new illumination condition. In doing so, we take inspiration from the light stage work of Debevec et al., who first demonstrated the ability to relight people captured in a controlled lighting environment. Whereas existing light stages require expensive, room-scale spherical capture gantries and exist in only a few labs in the world, we demonstrate how to acquire useful data from a normal TV or desktop monitor. Instead of subjecting the user to uncomfortable rapidly flashing light patterns, we operate on images of the user watching a YouTube video or other standard content. We train a deep network on images plus monitor patterns of a given user and learn to predict images of that user under any target illumination (monitor pattern). Experimental evaluation shows that our method produces realistic relighting results. Video results are available at http://grail.cs.washington.edu/projects/Light_Stage_on_Every_Desk/.