Learning Real-World Image De-weathering with Imperfect Supervision
DOI:
https://doi.org/10.1609/aaai.v38i4.28164Keywords:
CV: Low Level & Physics-based VisionAbstract
Real-world image de-weathering aims at removing various undesirable weather-related artifacts. Owing to the impossibility of capturing image pairs concurrently, existing real-world de-weathering datasets often exhibit inconsistent illumination, position, and textures between the ground-truth images and the input degraded images, resulting in imperfect supervision. Such non-ideal supervision negatively affects the training process of learning-based de-weathering methods. In this work, we attempt to address the problem with a unified solution for various inconsistencies. Specifically, inspired by information bottleneck theory, we first develop a Consistent Label Constructor (CLC) to generate a pseudo-label as consistent as possible with the input degraded image while removing most weather-related degradation. In particular, multiple adjacent frames of the current input are also fed into CLC to enhance the pseudo-label. Then we combine the original imperfect labels and pseudo-labels to jointly supervise the de-weathering model by the proposed Information Allocation Strategy (IAS). During testing, only the de-weathering model is used for inference. Experiments on two real-world de-weathering datasets show that our method helps existing de-weathering models achieve better performance. Code is available at https://github.com/1180300419/imperfect-deweathering.Downloads
Published
2024-03-24
How to Cite
Liu, X., Zhang, Z., Wu, X., Feng, C., Wang, X., Lei, L., & Zuo, W. (2024). Learning Real-World Image De-weathering with Imperfect Supervision. Proceedings of the AAAI Conference on Artificial Intelligence, 38(4), 3738-3746. https://doi.org/10.1609/aaai.v38i4.28164
Issue
Section
AAAI Technical Track on Computer Vision III