Recording dynamic facial micro-expressions with a multi-focus camera array

TL;DR

This paper introduces a multi-focus camera array system with 54 high-resolution cameras to capture detailed, dynamic facial micro-expressions across the entire face, significantly improving resolution and depth-of-field over traditional single-camera setups.

Contribution

The paper presents a novel multi-focus camera array design that captures high-resolution, dynamic facial videos with enhanced depth-of-field and resolution, surpassing traditional single-camera methods.

Findings

Achieved a uniform lateral resolution of ~26.75 micrometers across the face.

Extended the effective depth-of-field to approximately 43mm, nearly 10 times that of single-focus systems.

Demonstrated the system's capability to capture detailed micro-expressions on curved surfaces.

Abstract

We present an approach of utilizing a multi-camera array system for capturing dynamic high-resolution videos of the human face, with improved imaging performance as compared to traditional single-camera configurations. Employing an array of 54 individual high-resolution cameras, each with its own 13 megapixel sensor (709 megapixels total), we uniquely focus each camera to a different plane across the curved surface of the human face in order to capture dynamic facial expressions. Post-processing methods then stitch together each synchronized set of 54 images into a composite video frame. Our multi-focus strategy overcomes the resolution and depth-of-field (DOF) limitations for capturing macroscopically curved surfaces such as the human face, while maintaining high lateral resolution. Specifically we demonstrate how our setup achieves a generally uniform lateral resolution of 26.75 +/- 8.8 micrometer across a composite DOF of ~43mm that covers the entire face (85 cm^2 + FOV). Compared to a single-focus configuration this is almost a 10-fold increase in effective DOF. We believe that our new approach for multi-focus camera array video sets the stage for future video capture of a variety of dynamic and macroscopically curved surfaces at microscopic resolution.