Don't Look at the Camera: Achieving Perceived Eye Contact

TL;DR

This paper tackles the problem of how to elicit perceived eye contact when a person is captured by a camera and displayed on a screen. It employs a controlled gaze-perception study with eye-tracker–verified fixation across 11 vertical offsets and two viewing distances, analyzing responses with Gaussian and psychometric fits to identify the gaze offset that maximizes eye-contact perception. The key finding is that looking approximately $2^{\circ}$ below the camera center yields the strongest perceived eye contact, rather than direct lens fixation, at typical distances ($20$–$24$ inches). The work offers actionable guidance for photography and teleconferencing systems, enabling gaze-correction strategies that enhance social cues in camera-mediated communication. Overall, it advances our understanding of camera-relative gaze perception and provides practical design rules for realistic eye-contact cues in 2D renderings.

Abstract

We consider the question of how to best achieve the perception of eye contact when a person is captured by camera and then rendered on a 2D display. For single subjects photographed by a camera, conventional wisdom tells us that looking directly into the camera achieves eye contact. Through empirical user studies, we show that it is instead preferable to {\em look just below the camera lens}. We quantitatively assess where subjects should direct their gaze relative to a camera lens to optimize the perception that they are making eye contact.

Figures (3)

• Figure 1: Equipment set up used to collect pictures from gazers.
• Figure 2: Single trial during data collection for reporting subjective gaze perception. All trials were self-paced, and participants answered all questions for each picture they viewed.
• Figure 3: (a) Average distribution of ‘yes’ response across gaze offset with 95% CI and Gaussian fit showing a peak at 1.76° below 0° fixation (negative numbers indicate fixations above the center of the camera (0°), and positive numbers indicate fixations below the center). (b) Visual representation of the point of fixation (-1.76°) on an actor’s face to produce an impression of eye contact. The circular heatmap on the image of the actor corresponds to the Gaussian fit of perceived eye contact. The red center of the heatmap is the optimal perceived point of eye contact. As one moves further away from this point, towards the outer blue ring, so does the perception of eye contact being made. (c) Average distribution of ‘down’ response across gaze offset fitted with a psychometric function. ‘dva' stands for degrees of visual angle.