To address the problem, in this paper, we propose an unsupervised domain-classifier guided shadow removal network, DC-ShadowNet.
Ranked #1 on Shadow Removal on Adjusted ISTD
In this paper, given a single nighttime image as input, our goal is to enhance its visibility by increasing the dynamic range of the intensity, and thus can boost the intensity of the low light regions, and at the same time, suppress the light effects (glow, glare) simultaneously.
Second, we employ a gradual refinement scheme in which we start from a simple CRF model to generate a result which is more robust to noise but less accurate, and then we gradually increase the model's complexity to improve the result.
Initially, given a pair of synthetic fog images, its corresponding clean images and optical flow ground-truths, in one training batch we train our network in a supervised manner.
To address the problem, we introduce a network joining day/night translation and stereo.
We present a joint Structure-Stereo optimization model that is robust for disparity estimation under low-light conditions.