LPATR-Net: Learnable Piecewise Affine Transformation Regression Assisted Data-Driven Dehazing Framework

Jianming Wang

Abstract:

Nowadays, data-driven learning based deep neural
network (DNN) is the most dominant SOTA image dehazing
framework. Here, learning to perfectly simulate the underlying
mapping rules (from hazy to clear) told by massive paired
training data is its core driving force. However, under genuine
scenarios, it is extremely hard to guarantee the 100% qualifi
cation of all collected ground truth (GT) haze-free data. That’s
because natural weather is hardly controlled, and many weathers
are actually in a chaotic status existing between foggy and fog
free. Thus, unlike most supervised learning issues, the image
dehazing society is born with the torture of part of faulty ground
truth no-haze samples. Therefore, totally trusting training data
and solely pursuing more fitting powerful data-driven model
may not be a wise solution. To cope with this thorny challenge,
in this paper, instead of faithfully pursuing for fitting capacity
promotion, we on the contrary choose to intentionally cut down
the fitting flexibility to achieve higher-level robustness. That is
the LPATR-Net, a novel dehazing framework specially armed
with fitting power suppression mechanism to resist intrinsic
annoying faulty GT. This solution does not involve any extra
manually labeling. Specifically, the LPATR-Net architecture is
created completely around elaborately designed fitting-restrained
learnable piecewise a ne transformation regression. Since such
low-order linear regression structure genetically can only fit for
majority of data, the interference of minority of unqualified
GT samples is expected to be e ectively suppressed. Through
further coupled with a highly customized multi-concerns high
accuracy dehazing fitting companion component, All-Mattering,
proposed LPATR-Net elegantly achieves the seamless integration