Two-Step Image Dehazing with Intra-domain and Inter-domain Adaptation

TL;DR

This paper introduces a two-step image dehazing method that addresses both intra-domain and inter-domain distribution gaps, improving performance on synthetic and real datasets through targeted adaptation strategies.

Contribution

The paper proposes a novel two-step dehazing network with intra-domain and constrained inter-domain adaptation, effectively reducing distribution shifts within and across domains.

Findings

Outperforms state-of-the-art methods on synthetic datasets

Achieves superior results on real-world datasets

Effectively reduces intra- and inter-domain distribution gaps

Abstract

Caused by the difference of data distributions, intra-domain gap and inter-domain gap are widely present in image processing tasks. In the field of image dehazing, certain previous works have paid attention to the inter-domain gap between the synthetic domain and the real domain. However, those methods only establish the connection from the source domain to the target domain without taking into account the large distribution shift within the target domain (intra-domain gap). In this work, we propose a Two-Step Dehazing Network (TSDN) with an intra-domain adaptation and a constrained inter-domain adaptation. First, we subdivide the distributions within the synthetic domain into subsets and mine the optimal subset (easy samples) by loss-based supervision. To alleviate the intra-domain gap of the synthetic domain, we propose an intra-domain adaptation to align distributions of other subsets to the optimal subset by adversarial learning. Finally, we conduct the constrained inter-domain adaptation from the real domain to the optimal subset of the synthetic domain, alleviating the domain shift between domains as well as the distribution shift within the real domain. Extensive experimental results demonstrate that our framework performs favorably against the state-of-the-art algorithms both on the synthetic datasets and the real datasets.