TL;DR
This paper explores how mirror reflections alter the statistical properties of images, revealing pervasive low-level chiral signals and implications for various computer vision tasks.
Contribution
It introduces the concept of visual chirality, analyzing how reflection affects image data distributions and uncovering surprising chiral signals in visual datasets.
Findings
Low-level chiral signals are widespread in imagery.
Reflection influences data distributions used in computer vision.
Visual chirality can be detected in images of people and faces.
Abstract
How can we tell whether an image has been mirrored? While we understand the geometry of mirror reflections very well, less has been said about how it affects distributions of imagery at scale, despite widespread use for data augmentation in computer vision. In this paper, we investigate how the statistics of visual data are changed by reflection. We refer to these changes as "visual chirality", after the concept of geometric chirality - the notion of objects that are distinct from their mirror image. Our analysis of visual chirality reveals surprising results, including low-level chiral signals pervading imagery stemming from image processing in cameras, to the ability to discover visual chirality in images of people and faces. Our work has implications for data augmentation, self-supervised learning, and image forensics.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Visual Chirality· youtube
