Accurate Transmission Estimation for Removing Haze and Noise from a Single Image

Abstract

Image noise usually causes depth-dependent visual artifacts in single image dehazing. Most existing dehazing methods exploit a two-step strategy in the restoration, which inevitably leads to inaccurate transmission maps and low-quality scene radiance for noisy and hazy inputs. To address these problems, we present a novel variational model for joint recovery of the transmission map and the scene radiance from a single image. In the model, we propose a transmission-aware non-local regularization to avoid noise amplification by adaptively suppressing noise and preserving fine details in the recovered image. Meanwhile, to improve the accuracy of transmission estimation, we introduce a semantic-guided regularization to smooth out the transmission map while keeping depth inconsistency at the boundaries of different objects. Furthermore, we design an alternating scheme to jointly optimize the transmission map and the scene radiance as well as the segmentation map.

Existing System

Non-local Total Variation (NLTV), Gradient Residual Minimization (GRM)

Proposed System

The contributions of the work are summarized as follows. We optimize the haze-free image J and the transmission map t in a unified framework, which can effectively suppress the depth-dependent noise in the dehazed results and mitigate the inherited noise in the estimated transmission maps. We propose a transmission-aware regularization based on our regression weight function and NLTV to adaptively constrain J. This weight function can provide appropriate constraints for NLTV to preserve fine details while reducing noise in the recovery of radiance. We design a semantic-guided regularization based on the edge consistency between ground-truth transmission maps and semantic annotation maps. This regularization utilizes semantic segmentation maps to guide the smoothness of transmission maps inside object regions while preserving the depth edges at object boundaries.

Architecture

BLOCK DIAGRAM