One mainstream of image anomaly detection is based on reconstruction. Such methods still struggle with diverse anomalies, such as near-in-distribution or deformed types. To address the challenge, we propose a Discriminative Network with Dual Reconstruction (DN-DR), consisting of a Memory Reconstructor, a Corrector, and a Discriminator. DN-DR aims to better restore the defective image to its normal state through dual reconstruction, thereby obtaining superior Discriminator performance. Specifically, (1) the Memory Reconstructor is based on training multi-scale codebooks from normal images to rebuild unknown regions in the test images, also named preliminary reconstruction; (2) the Corrector, as a subsequent reconstruction module, addresses false anomalies caused by the patch-level replacement strategy in the Memory Reconstructor, achieving a final refined reconstruction; (3) a U-Net Discriminator follows. Experiments on the challenging MVTec AD dataset demonstrate excellent reconstruction performance and anomaly inspection, including defects of near-in-distribution or deformed types.

Currently, image-denoising methods based on deep learning cannot adequately reconcile contextual semantic information and spatial details. To take these information optimizations into consideration, in this paper, we propose a Context-Space Progressive Collaborative Network (CS-PCN) for image denoising. CS-PCN is a multi-stage hierarchical architecture composed of a context mining siamese sub-network (CM2S) and a space synthesis sub-network (3S). CM2S aims at extracting rich multi-scale contextual information by sequentially connecting multi-layer feature processors (MLFP) for semantic information pre-processing, attention encoder-decoders (AED) for multi-scale information, and multi-conv attention controllers (MCAC) for supervised feature fusion. 3S parallels MLFP and a single-scale cascading block to learn image details, which not only maintains the contextual information but also emphasizes the complementary spatial ones. Experimental results show that CS-PCN achieves significant performance improvement in synthetic and real-world noise removal.

Image restoration is an ill-posed problem due to the infinite feasible solutions for degraded images. Although CNN-based and Transformer-based approaches have been proven effective in image restoration, there are still two challenges in restoring complex degraded images: 1)local-global information extraction and fusion, and 2)computational cost overhead. To address these challenges, in this paper, we propose a lightweight image restoration network (CLG-INet) based on CNN-Transformer interaction, which can efficiently couple the local and global information. Specifically, our model is hierarchically built with a "sandwich-like" structure of coupling blocks, where each block contains three layers in sequence (CNN-Transformer-CNN). The Transformer layer is designed with two core modules: Dynamic Bi-Projected Attention (DBPA), which performs dual projection with large convolutions across windows to capture long-range dependencies, and Gated Non-linear Feed-Forward Network (GNFF), which reconstructs mixed feature information. In addition, we introduce interactive learning, which fuses local features and global representations in different resolutions to the maximum extent. Extensive experiments demonstrate that CLG-INet significantly boosts performance on various image restoration tasks, such as deraining, deblurring, and denoising.

Based on curvelet transform this paper embeds one leveled watermark onto significant coefficients by quantization in individual frequency scales. Watermark bits come from image HASH, which is defined in the paper. Bigger coefficients are used for watermarking for the conception that coefficient energy is proportion to its directional sensitivity and bigger coefficients are more stable. Watermark is extracted without resort to the original image. The proposed watermarking can realize multifunction of content authentication and copyright protection the same time.

Multipurpose watermarking for content authentication and copyright verification are accomplished by using the multiscale curvelet transform. A curvelet transform gains better and sparser representation than most traditional multiscale transforms. In this paper, an image is decomposed into multiscale coefficients with a dyadic number of wedges constructed from a variety of neighboring scales. Image hash is designed to extract image features from an approximate scale. The image features represented in the form of bit sequences are then embedded onto the wedges by a quantization based on human visual system behavior. The implementation strategy achieves content authentications for fatigue watermarking and copyright verifications for robust watermarking. The experiments demonstrate good results to support the feasibility of using this method in multipurpose applications.