PoTATO: A Dataset for Analyzing Polarimetric Traces of Afloat Trash Objects

Plastic waste in aquatic environments poses severe risks to

marine life and human health. Autonomous robots can be utilized to

collect floating waste, but they require accurate object identification ca-

pability. While deep learning has been widely used as a powerful tool for

this task, its performance is significantly limited by outdoor light condi-

tions and water surface reflection. Light polarization, abundant in such

environments yet invisible to the human eye, can be captured by mod-

ern sensors to significantly improve litter detection accuracy on water

surfaces. With this goal in mind, we introduce PoTATO, a dataset con-

taining 12,380 labeled plastic bottles and rich polarimetric information.

We demonstrate under which conditions polarization can enhance object

detection and, by providing raw image data, we offer an opportunity for

theresearchcommunitytoexplorenovelapproachesandpushthebound-

aries of state-of-the-art object detection algorithms even further. Code

and data are publicly available at https://github.com/luisfelipewb/

PoTATO/tree/eccv2024.