Hyperspectral image shadow compensation via cycle-consistent adversarial networks

Adaptive Shadow Compensation Method in Hyperspectral Images via Multi-Exposure Fusion and Edge Fusion

“…This allows it to avoid issues such as overexposure, blurred details, and unnatural transitions. -f) results from MSR [43], SC-CycleGAN [16], MF [8], ISR [44], and our method. The red and blue dots represent the selected pixels in the shadowed and non-shadowed areas, respectively.…”

“…Windrim et al [17] developed a method to generate shadow-invariant hyperspectral image features using deep learning and physics-based illumination modeling, eliminating the need for labeled data or extra sensors. Zhao et al [16] introduced an unsupervised method for shadow compensation in hyperspectral images, effectively transforming shadowed regions to non-shadowed areas without the need for paired samples or prior shadow detection.…”

“…In this work, four mainstream shadow compensation methods are used for comparison with the proposed method: MSR [43] (Multi-Scale Retinex), SC-CycleGAN [16] (Shadow Compensation via Cycle-Consistent Adversarial Networks), MF [8] (Multi-exposure Fusion) and ISR [44] (Interactive Shadow Removal). The MSR processes images with Gaussian blur and then calculates the logarithmic difference between the original image and the Gaussian blurred image to obtain the Retinex image.…”

“…They achieved this by extracting spectra from both shadowed and non-shadowed areas and using a nonlinear model to evaluate pixel abundance, then reconstructing pixels in shadowed regions. Zhao et al [16] developed a network based on the CycleGAN (Cycle-Consistent Generative Adversarial Network), named SC-CycleGAN, eliminating the need for paired training data and shadow detection. The network, comprising two generators and two discriminators, learns to map between shadowed and non-shadowed domains, effectively compensating shadows while preserving the integrity of non-shadowed areas.…”

A Coarse‐To‐Fine Approach to Detect Shadows in the Chang’E−4 VNIS Hyperspectral Images

“…(2011) proposed to separate shadow and nonshadow pixels by dynamically generating a feature space from shadow samples. Machine learning has also been applied in shadow detection using convolutional deep neural networks (Chen et al., 2020; Khan et al., 2016; Luo et al., 2020; Ma et al., 2021; Zhang & Liu, 2021; Zhao et al., 2021). (d) Object segmentation.…”