FALCON: Fast Image Haze Removal Leveraging Continuous Density Mask

Donghyun Kim, Seil Kang, Seong Jae Hwang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2025, pp. 853-863

Image dehazing, eliminating atmospheric interference like fog and haze, remains a pervasive challenge crucial for robust vision applications such as surveillance and remote sensing under adverse visibility. While various methodologies have evolved, they innately prioritize dehazing quality metrics, neglecting the need for real-time applicability in time-sensitive domains like autonomous driving. Considering the need for a pioneering hybrid paradigm in dehazing, we present FALCON, a single-image dehazing system achieving state-of-the-art performance on both quality and speed. Particularly, we leverage the underlying haze distribution via a novel approach called Continuous Density Mask (CDM). CDM serves as a continuous-valued mask input prior and auxiliary loss, allowing model to explicitly identify pixel-wise haze density. We also implement the haze density calculation in a differentiable manner. Further, we introduce a low model-workload recipe that globally expand the receptive field by adding a single bottleneck module to U-Net. Comprehensive experiments involving multiple state-of-the-art methods and analyses demonstrate FALCON's exceptional performance in both dehazing quality and speed (i.e., >180 frames-per-second).