.png){kind=icon}
.png){kind=icon}
Return
RenHaze: A Coarse-to-Fine Rendering Framework for Improving Robustness to Haze
.png){kind=icon}
PRE
AI
T
S
Q
Z
DOI：10.1145/3770745.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Large-scale datasets centered on images have driven advancements in deep learning-based computer vision applications. While there is an abundance of datasets containing images depicting favorable weather scenes, datasets featuring images of adverse weather conditions, especially the presence of haze, are scarce due to challenges in their collection. In response, we leverage the advantages of deep learning techniques to introduce a novel approach for facilitating the rendering of realistic and diverse hazy images, named RenHaze. To be specific, RenHaze adopts a denseness parameter o to control the haze level of output images and consists of five subnets, including a content exploitation (CE) subnet, a depth exploitation (DE) subnet, a haze exploitation (HE) subnet, an image generation (IG) subnet, and an image discernment (ID) subnet. The CE, DE, and HE subnets are responsible for extracting features from the source clear image, depth image, and reference hazy image, respectively, and then providing them for the IG subnet. The IG subnet is used to perform image translation in a coarse-to-fine manner, while the ID subnet is employed to discern the realism of the rendered image and provide feedback to the IG subnet for generating the desired output. Extensive experiments demonstrate the superiority of the proposed model over competing IG methods in terms of the realism and diversity of synthesized hazy images, as well as its effectiveness in boosting the performance of computer vision tasks such as object detection and semantic segmentation in real-world hazy environments.
Keywords:
Image rendering
hazy image
I2I
Deep learning
Journal
IF:
6.6
Papers:
1.5K
Citations:
6.2K
Organization
Cited Papers