Dual Gradient Based Snow Attentive Desnowing

Abstract

In this paper, we propose a novel dual gradient-based desnowing algorithm that can accurately remove snow from a scene by characterizing snow particles. To localize snow in an image, we present a gradient-based snow activation map that can be estimated using snow classification. To recognize various patterns in the shapes and trajectories of snow particles, we introduce a gradient-based snow edge map. Using these two gradients, we estimate an accurate snow attention mask that is subsequently used for snow removal. In addition, we propose a translucency-aware context restoration network to handle various degrees of snow transparency and thus, prevent our method from losing the image context information during desnowing. Experimental results demonstrate that the proposed method considerably outperforms other state-of-the-art desnowing algorithms quantitatively and qualitatively.

Restoring Snow-Degraded Single Images With Wavelet in Vision Transformer

“…The restoration of single images degraded by particles of snow adverse weather is an established ill-posed problem that has attracted a lot of research attention since the era of deep-learning [1], [4], [5], [6], [7], [8], [9], [22], [23], [24], [25], [26], [27], [28], [29]. In [1], Liu et al proposed a multistage context-aware network (dubbed DesnowNet) to deal with the complicated size, density, opaque and translucent characteristics of snow particle removal.…”

“…In [28] (DDMSNet). Further scholarly works [5], [8], [25] have also attempted to restore snow-degraded images with generative adversarial networks (GAN). Recently, the emerging unified models designed for multiple noise elements' removal have begun to include desnow tasks in their portfolio.…”