FLUID: Few-Shot Self-Supervised Image Deraining

Rai, Shyam Nandan and Saluja, Rohit and Arora, Chetan and Balasubramanian, Vineeth N and et al, . (2022) FLUID: Few-Shot Self-Supervised Image Deraining. In: 22nd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022, 4 January 2022 through 8 January 2022, Waikoloa.

[img] Text
Proceedings_2022_IEEE_CVF.pdf - Published Version
Restricted to Registered users only

Download (3MB) | Request a copy


Self-supervised methods have shown promising results in denoising and dehazing tasks, where the collection of the paired dataset is challenging and expensive. However, we find that these methods fail to remove the rain streaks when applied for image deraining tasks. The method's poor performance is due to the explicit assumptions: (i) the distribution of noise or haze is uniform and (ii) the value of a noisy or hazy pixel is independent of its neighbors. The rainy pixels are non-uniformly distributed, and it is not necessarily dependant on its neighboring pixels. Hence, we conclude that the self-supervised method needs to have some prior knowledge about rain distribution to perform the deraining task. To provide this knowledge, we hypothesize a network trained with minimal supervision to estimate the likelihood of rainy pixels. This leads us to our proposed method called FLUID: Few Shot Sel f-Supervised Image Deraining.We perform extensive experiments and comparisons with existing image deraining and few-shot image-to-image translation methods on Rain 100L and DDN-SIRR datasets containing real and synthetic rainy images. In addition, we use the Rainy Cityscapes dataset to show that our method trained in a few-shot setting can improve semantic segmentation and object detection in rainy conditions. Our approach obtains a mIoU gain of 51.20 over the current best-performing deraining method. [Project Page] © 2022 IEEE.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Balasubramanian, Vineeth Nhttps://orcid.org/0000-0003-2656-0375
Item Type: Conference or Workshop Item (Paper)
Additional Information: This work was partly funded by IHub-Data at IIIT-Hyderabad and DST through the IMPRINT program.
Uncontrolled Keywords: Few-shot; Semi- and Un- supervised Learning Scene Understanding; Transfer; Vision Systems and Applications
Subjects: Computer science
Divisions: Department of Computer Science & Engineering
Depositing User: . LibTrainee 2021
Date Deposited: 23 Jul 2022 07:28
Last Modified: 23 Jul 2022 07:28
URI: http://raiith.iith.ac.in/id/eprint/9882
Publisher URL: http://doi.org/10.1109/WACV51458.2022.00049
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 9882 Statistics for this ePrint Item