DeepAI AI Chat
Log In Sign Up

Image Dehazing using Bilinear Composition Loss Function

by   Hui Yang, et al.

In this paper, we introduce a bilinear composition loss function to address the problem of image dehazing. Previous methods in image dehazing use a two-stage approach which first estimate the transmission map followed by clear image estimation. The drawback of a two-stage method is that it tends to boost local image artifacts such as noise, aliasing and blocking. This is especially the case for heavy haze images captured with a low quality device. Our method is based on convolutional neural networks. Unique in our method is the bilinear composition loss function which directly model the correlations between transmission map, clear image, and atmospheric light. This allows errors to be back-propagated to each sub-network concurrently, while maintaining the composition constraint to avoid overfitting of each sub-network. We evaluate the effectiveness of our proposed method using both synthetic and real world examples. Extensive experiments show that our method outperfoms state-of-the-art methods especially for haze images with severe noise level and compressions.


page 2

page 3

page 5

page 7

page 8


Joint Transmission Map Estimation and Dehazing using Deep Networks

Single image haze removal is an extremely challenging problem due to its...

Estimation of non-symmetric and unbounded region of attraction using shifted shape function and R-composition

A general numerical method using sum of squares programming is proposed ...

Every Untrue Label is Untrue in its Own Way: Controlling Error Type with the Log Bilinear Loss

Deep learning has become the method of choice in many application domain...

Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement

Real-world low-light images suffer from two main degradations, namely, i...

KinD-LCE Curve Estimation And Retinex Fusion On Low-Light Image

The problems of low light image noise and chromatic aberration is a chal...

JigsawNet: Shredded Image Reassembly using Convolutional Neural Network and Loop-based Composition

This paper proposes a novel algorithm to reassemble an arbitrarily shred...

A Fast Deep Learning Network for Automatic Image Auto-Straightening

Rectifying the orientation of images represents a daily task for every p...