The remarkable success of AI-Generated Content (AIGC), especially diffusion image generation models, brings about unprecedented creative applications, but also creates fertile ground for malicious counterfeiting and crime. A highly effective family of forgery image detection methods based on diffusion reconstruction error has emerged, as images generated by diffusion are more easily reconstructed by any diffusion model. However, we find that existing methods only use reconstruction error from a single time step, failing to fully leverage the entire reconstruction process. To this end, we propose to comprehensively consider every single time step to form the Temporal Reconstruction Error (TRE) that offers a richer feature representation. Furthermore, we design temporal aggregation and spatial focusing modules from two dimensions respectively to more effectively extract discriminative information from the TRE feature. Finally, we validate the proposed method on two popular datasets, and experimental results demonstrate that the proposed approach achieves state-of-the-art performance.

Generative Adversarial Network (GAN), as a popular generative model in the field of Artificial Intelligence Generated Content (AIGC), has been intensively developed in previous research, with significant improvements in the quality and diversity of image generation. However, there are still many cases where the results are not satisfactory. A primary concern pertains to the chaotic and blurred local details within the generated images. In this work, through the diagnosis and analysis of high-quality and low-quality images produced by the GAN model, we identified that this issue stems from inherent semantic errors of the GAN, that is, convolutional kernels responsible for certain semantics are not properly involved in the generation process of corresponding image regions. To this end, we propose a straightforward yet effective treatment method, which constrains each image region to be generated by its corresponding semantic convolutional kernels. Experimental results demonstrate that our proposed optimization method can improve the issue of chaotic and blurred local regions in generated images and enhance the overall generation quality. Our work pioneers a novel paradigm for diagnosing and treating GANs, driving the research development and practical application of AIGC image generation technology.

VTON (Virtual Try-ON), as an innovative visual application in e-commerce scenarios with great commercial value, has been widely studied in recent years. Due to its better robustness and realistic effect, deformation-synthesize-based VTON has become the dominant approach in this field. Existing clothing deformation techniques optimize the mapping relations between the original clothing image and the ground truth (GT) image of the worn clothing. However, there are color differences between the original and GT clothing images caused by lighting, warping, and occlusion. The color differences may lead to misaligned clothing mapping by only minimizing the cost of pixel value difference. Another drawback is that taking the parsing prediction as GT will bring alignment remnant, rooting in the processing order of parsing and deformation. Aiming above two drawbacks, we put forward SAME-VTON (Self-Adaptive clothing Mapping basEd Virtual Try-ON) for achieving realistic virtual try-on results. The core of SAME-VTON is the self-adaptive clothing mapping technique, composed of two parts: a color-adaptive clothing mapping module and a parsing-adaptive prediction process. In the color-adaptive clothing mapping module, we map each pixel of the target clothing with a combination of multiple pixel values from the original clothing image, which considers both the position and color changes. Furthermore, different combination weights are learned to increase the diversity of color mapping. In the parsing-adaptive prediction process, the color-adaptive clothing mapping module is adopted to deform clothing first, then the human parsing result is predicted under the reference of the deformed clothing, which can avoid alignment remnant. Extensive experiments demonstrate that the proposed SAME-VTON with the self-adaptive clothing mapping technique can achieve optimal mapping in the case of large color differences and obtain superior results compared with existing deformation-synthesize-based VTON.

The development of online economics arouses the demand of generating images of models on product clothes, to display new clothes and promote sales. However, the expensive proprietary model images challenge the existing image virtual try-on methods in this scenario, as most of them need to be trained on considerable amounts of model images accompanied with paired clothes images. In this paper, we propose a cheap yet scalable weakly-supervised method called Deep Generative Projection (DGP) to address this specific scenario. Lying in the heart of the proposed method is to imitate the process of human predicting the wearing effect, which is an unsupervised imagination based on life experience rather than computation rules learned from supervisions. Here a pretrained StyleGAN is used to capture the practical experience of wearing. Experiments show that projecting the rough alignment of clothing and body onto the StyleGAN space can yield photo-realistic wearing results. Experiments on real scene proprietary model images demonstrate the superiority of DGP over several state-of-the-art supervised methods when generating clothing model images.

Image virtual try-on task has abundant applications and has become a hot research topic recently. Existing 2D image-based virtual try-on methods aim to transfer a target clothing image onto a reference person, which has two main disadvantages: cannot control the size and length precisely; unable to accurately estimate the user's figure in the case of users wearing thick clothing, resulting in inaccurate dressing effect. In this paper, we put forward an akin task that aims to dress clothing for underwear models. To solve the above drawbacks, we propose a Shape Controllable Virtual Try-On Network (SC-VTON), where a graph attention network integrates the information of model and clothing to generate the warped clothing image. In addition, the control points are incorporated into SC-VTON for the desired clothing shape. Furthermore, by adding a Splitting Network and a Synthesis Network, we can use in-shop clothing/model pair data to help optimize the deformation module and generalize the task to the typical virtual try-on task. Extensive experiments show that the proposed method can achieve accurate shape control. Meanwhile, compared with other methods, our method can generate high-resolution results with detailed textures, which can be applied in real applications.

A critical aspect for exploring the biological function of a microRNA (miRNA) lies on exact detection and validation of its target mRNAs. However, no convenient and efficient web-based server is available for plant biologists to identify the experimentally verified target mRNAs of miRNAs. In this work, we built a comprehensive web-based platform for miRNA-target analysis, named as Whole-degradome-based Plant MiRNA-target Interaction Analysis Server (WPMIAS), for validation of predicted interactions of miRNAs and their target mRNAs (MTIs) by user-submitted data or all available pre-loaded degradome data. Besides, the server can construct degradome-based miRNA regulatory networks (MRNs) based on the validated MTIs to help study the functions and relations among miRNAs and target mRNAs. WPMIAS is also suitable for other small RNAs (sRNAs), such as 21-nt phased siRNAs (phasiRNAs) and natural antisense siRNAs (nat-siRNAs), which direct cleavage of target mRNAs. Currently, WPMIAS supports 64 plant species with ∼200 cDNA libraries and 274 pre-loaded plant degradome datasets. The user can identify all validated MTIs by analyzing all degradome data at a time and understand when and where MTIs take place and their cleavage levels. With the data obtained from WPMIAS, the user can build a plant miRNA-target map, where it is convenient to find interesting research ideas on miRNAs. In summary, WPMIAS is able to support a comprehensive web-based plant miRNA-target analysis and expected to greatly promote future research on plant miRNAs. AVAILABILITY: It can be freely accessed at https://cbi.njau.edu.cn/WPMIAS/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.