Abstract
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.
Abstract (translated)
水面漂浮物的精确分割往往受到表面反光和变化的户外照明的影响。偏振成像提供了一种单传感器途径，可以减轻干扰语义分割的水面反光问题。我们在PoTATO数据集上对最先进的融合网络进行了基准测试，该数据集包含内陆水域中塑料瓶的偏振图像，并将其性能与使用传统模型的单一图像基线进行了比较。我们的结果表明，偏振线索有助于恢复低对比度物体并抑制反射引起的假阳性，相对于RGB输入而言，平均交并比（IoU）更高且轮廓误差更低。这些更清晰的掩码也带来了一定的成本：额外的通道会增加模型大小、计算负载以及引入新假阳性的风险。通过提供可重复使用的诊断基准和公开可用的代码，我们希望帮助研究人员选择偏振相机是否适合他们的应用，并加速相关研究的发展。
URL
https://arxiv.org/abs/2509.24731
