Single Image Dehazing by Multi-Scale Fusion

By Codruta Orniana Ancuti, Cosmin Ancuți. IEEE Transactions on Image Processing, 2013

665 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/f285616c9093679b68f9b5914d7b8b448633b9c3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Referenceless Prediction of Perceptual Fog Density and Perceptual Image Defogging (2015, methodology): “In [17], three weight maps were defined based on measurements of chrominance, saturation, and saliency.”
A fusion-based enhancing method for weakly illuminated images (2016, methodology): “Method [43] fails to enhance the image.”
NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images (2020, methodology): “Another direction of research in image dehazing includes those methods that restore the visibility of hazy image without assuming the optical model [38, 1, 17].”
Gated Context Aggregation Network for Image Dehazing and Deraining (2018, methodology): “With the latest advances of deep learning, many CNN-based methods [1, 3, 31, 22, 32, 42] are proposed by leveraging a large scale training datasets.”
I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images (2018, background): “Fusion-based single image dehazing approaches [13], [23] have also achieved visually pleasant results without explicit transmission estimation and, more recently, several machine learning based methods have been introduced [17], [24], [25].”
Single Image Dehazing via Multi-scale Convolutional Neural Networks with Holistic Edges (2019, background): “Most dehazing methods use a variety of visual cues to capture deterministic and statistical properties of hazy images (Ancuti and Ancuti 2013; He et al. 2009, 2011; Ren and Cao 2017; Tan 2008; Tang et al. 2014; Zhu et al. 2015).”
O-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Outdoor Images (2018, background): “Recently many strategies [15, 39, 20, 41, 25, 6, 5, 1, 16, 2, 14, 40] addressed this problem , by considering different kinds of priors to estimate the transmission.”
Color Balance and Fusion for Underwater Image Enhancement (2018, methodology): “Image fusion has shown utility in several applications such as image compositing [52], multispectral video enhancement [53], defogging [23], [54] and HDR imaging [55].”
Gated Fusion Network for Single Image Dehazing (2018, methodology): “The network described in the previous subsection is subject to halo artifacts, particularly for strong transitions within the conﬁdence maps [1, 5].”
Single Image Dehazing via Conditional Generative Adversarial Network (2018, background): “In recent years, we have witnessed significant advances in image dehazing mainly due to using hand-crafted features to estimate transmission maps and atmospheric lights [1, 3, 4, 10, 11, 19, 20, 22, 40].”
Non-local Image Dehazing (2016, methodology): “7 and 8 compare our results to state-of-the-art single image dehazing methods [1, 3, 4, 5, 12, 19].”
Dense-Haze: A Benchmark for Image Dehazing with Dense-Haze and Haze-Free Images (2019, background): “Another category is represented by multi-scale fusion approaches [17], [18] that enhance the hazy scenes without explicitly estimating the transmission map.”
Densely Connected Pyramid Dehazing Network (2018, methodology): “Inspired by the previous methods that use multi-level features for estimating the transmission map [33, 5, 42, 1, 24], we propose a densely connected encoderdecoder structure that makes use of the features from multiple layers of a CNN, where the dense block is used as the basic structure.”