Purpose: The purpose of this paper is to present an efficient algorithm for multi-layer garment fitting simulation based on the geometric method to solve the low time cost problem during penetration detection and processing. This is more practical to design a CAD system to preview the multi-layer garment fitting effect in daily life. Design/methodology/approach: The construction of a multi-layer garment based on existing 3D garments is a suitable method because this method is similar to the daily method of multi-layer dressing. The major problem is the penetration phenomenon between different garments because these 3D garment’s geometric shapes are constructed in different situations. In this paper, an efficient algorithm of multi-layer garment simulation is reported. A face-face intersection detection algorithm is designed to detect the penetration region between multi-layer garments fast and a geometric penetration processing algorithm is presented to solve the penetration phenomenon during multi-layer garment simulation. Findings: This method can quickly detect the penetration between faces, and then deal with the penetration for multi-layer garment construction. Experimental results show that this method can not only remove the penetration but basically maintain the trend of wrinkles efficiently. At the same time, the garments used in the experiment have almost more than 5,800 faces, but the resolving time is under five seconds. Originality/value: The main originalities of the multi-layer garment virtual fitting algorithm based on the geometric method are highly efficient both in terms of time cost and fitting effect. Based on this method, the technology of multi-layer garment virtual fitting can be used to design a novel CAD system to preview the multi-layer garment fitting effect in real time. This is a pressing requirement of virtual garment applications.
Haze can cause a significant reduction in the contrast and brightness of images. CNN-based methods have achieved benign performance on synthetic data. However, they show weak generalization performance on real data because they are only trained on fully labeled data, ignoring the role of natural data in the network. That is, there exists distribution shift. In addition to using little real data for training image dehazing networks in the literature, few studies have designed losses to constrain the intermediate latent space and the output simultaneously. This paper presents a semi-supervised neural process dehazing network with asymmetry pseudo labels. First, we use labeled data to train a backbone network and save intermediate latent features and parameters. Then, in the latent space, the neural process maps the latent features of real data to the latent space of synthetic data to generate one pseudo label. One neural process loss is proposed here. For situations where the image may be darker after dehazing, another pseudo label is created, and one new loss is used to guide the dehazing result at the output end. We combine the two pseudo labels with designed losses to suppress the distribution shift and guide better dehazing results. Finally, the artificial and hazy natural images are tested experimentally to demonstrate the method’s effectiveness.
5 June 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Joint video moment retrieval and highlight detection is an emerging and challenging research task. It requires the generation of robust joint task features to satisfy the demands of video moment retrieval and video highlight detection. Moreover, it involves the interaction of multiple modalities. Presently, methods typically focus on the design of distinct enhancement modules and the addition of supplementary input data to improve the solution for joint video moment retrieval and highlight detection. However, they overlook subtask interference during joint training. Joint task learning leverages the correlations and complementarities between tasks, yet it also introduces task interference arising from the differences between tasks. In order to address task interference, we proposes a subtask prior-driven optimized mechanism. The mechanism consists of two stages. In the free stage, we train subtask model to get subtask prior features. In the constrained stage, the joint task model is constrained by the subtask. Besides, we propose a cross adaptive-gated mechanism. It addresses the issue of information loss in cross-modal fusion and filters out redundant information by conducting cross-modal interaction during feature compression and an adaptive gating process. Extensive experimental results exhibit the effectiveness of the subtask prior-driven optimized mechanism and the cross adaptive-gated transformer in joint video moment retrieval and highlight detection.