2025/09/29 by Luis Felipe Wolf Batista, Batista, Luis F. W., Tom Bourbon +3
Environmental Science · #Computer Vision and Pattern Recognition (cs.CV) #Coral and Marine Ecosystems Studies #FOS: Computer and information sciences #Marine and fisheries research #Robotics (cs.RO) #Water Quality Monitoring Technologies
paper · pdf · doi:10.48550/arxiv.2509.24731
openalex publication_date 2025/09/29 · openalex created_date 2025/10/01 · openalex updated_date 2026/07/28
Accurate segmentation of floating debris on water is often compromised by surface glare and changing outdoor illumination. Polarimetric imaging offers a single-sensor route to mitigate water-surface glare that disrupts semantic segmentation of floating objects. We benchmark state-of-the-art fusion networks on PoTATO, a public dataset of polarimetric images of plastic bottles in inland waterways, and compare their performance with single-image baselines using traditional models. Our results indicate that polarimetric cues help recover low-contrast objects and suppress reflection-induced false positives, raising mean IoU and lowering contour error relative to RGB inputs. These sharper masks come at a cost: the additional channels enlarge the models increasing the computational load and introducing the risk of new false positives. By providing a reproducible, diagnostic benchmark and publicly available code, we hope to help researchers choose if polarized cameras are suitable for their applications and to accelerate related research.