A robust and efficient image de-fencing approach using conditional generative adversarial networks

Seeing through obstructions with diffractive cloaking

“…To perform automatic obstruction detection, earlier methods assume regular or near-regular obstructions [Farid et al 2016;Liu et al 2008]. More recently, deep learning methods have been proposed for more robust detection [Gupta et al 2021;Hao et al 2019;Qian et al 2018]. Such methods usually focus on a particular type of obstruction to achieve robust obstruction detection, and struggle with complex scene structure.…”

“…Also, such approaches often fail on test inputs deviating from the training input distributions. Single-image inpainting approaches that aim to recover the latent obstructed image regions [Farid et al 2016;Gupta et al 2021;Qian et al 2018; do not constitute a valid alternative, as they often produce fictitious hallucinations for large occluded regions.…”

De-Fencing and Multi-Focus Fusion Using Markov Random Field and Image Inpainting

“…Restoration homographic matrices, dictionary based on k-means labeling, exemplar based inpainting manual initialization Deep learning based methods [11], [12], [13], [14], [15], [16], [17], [18], [19], [20] De-fencing adversarial, structural [21], [22], [23], [24], [25] Fusion multi-scale decomposition, dictionary-learning, nuclear norm regularizer, morphologies constraints, adaptive fusion rules, fractional differential coefficients, geometric sparse coefficients overcomplete dictionary, patch based clustering, single dictionary learning time efficiency, separate fusion and noise removal tasks, information loss due to channel-wise processing Model based methods [26], [27], [28], [29], [30], [31], [32], [33] [34], [35], [36], [37] Fusion SSIM, encoder features, K-means clustering, NSCT, Coupled-Neural-Ps consistency verification photo realistic fusion, blocking artifacts, post processing complete contours; and generator-discriminator setting for prediction of contour completion. In [3], subtraction based on gray-scale binarization is applied on multi-focus auxiliary images to obtain initial mask for image inpainting.…”

“…However, the scheme sometimes produces blobs in resultant image. In [12], single stage image de-fencing network based on adversarial, structural and perceptual information is proposed. The scheme provides promising results, however, requires multiple GPUs and training data.…”

“…However, the scheme requires manual selection of fence pixels carefully. Gupta et al [20], proposed image de-fencing framework based on cascaded adversarial networks. First network outputs the binary mask, while, the second network generates fence free image.…”