Perfect image compositing can harmonize the appearance between the foreground and background effectively so that the composite result looks seamless and natural. However, the traditional convolutional neural network (CNN)-based methods often fail to yield highly realistic composite results due to overdependence on scene parsing while ignoring the coherence of semantic and structural between foreground and background. In this paper, we propose a framework to solve this problem by training a stacked generative adversarial network with attention guidance, which can efficiently create a high-resolution, realistic-looking composite. To this end, we develop a diverse adversarial loss in addition to perceptual and guidance loss to train the proposed generative network. Moreover, we construct a multi-scenario dataset for high-resolution image compositing, which contains high-quality images with different styles and object masks. Experiments on the synthesized and real images demonstrate the efficiency and effectiveness of our network in producing seamless, natural, and realistic results. Ablation studies show that our proposed network can improve the visual performance of composite results compared with the application of existing methods.

To solve the problems of texture blurring and structure inconsistency in large area image inpainting. This paper proposes an image inpainting method based on multi-scale feature fusion. We design a multi-scale feature fusion module to expand the receptive field. Besides, we devise attention module to capture information from distant areas in the feature map. In this paper, partial convolution and recursive structure are adopted to repair the boundary of the missing area progressively. This method can continuously strengthen the constraint on the center of the missing region and make the repair results more refined. Experimental results show that, compared with the existing image inpainting methods, this structure improves the performance of image inpainting, and the image quality generated by it is the best.

There are many existing video restoration frameworks, but there are no professional methods to deal with multiple degradation restorations of vintage films. With the help of the idea of mapping, this paper constructs a model with two variational autoencoders to repair the complex degradation problem. In addition, convolutional LSTM is used for video de-flicker processing to obtain smoother and natural results. The experimental results prove that this method can repair different damages in the vintage films screen at the same time, and achieve good results.

Currently, common three-dimensional (3D) human pose estimation algorithms achieve good results in representation learning, but still suffer from poor estimation accuracy and depth ambiguity at the joint points of the human skeleton, and extracting the image context is highly promising for mitigating the depth ambiguity. Therefore, an effective way to estimate human pose from monocular video images using redundant two-dimensional (2D) pose sequence spatio-temporal information is a research challenge. Many existing studies have mostly attempted to capture the spatial as well as temporal relationships of human poses in videos to solve these two problems. However, these works tend to overlook the fact that the lack of remote dependency modeling capabilities and parallelism makes the estimated 3D human poses often less accurate. We have proposed a Recurrent Transformer that can achieve a good balance between its efficiency and model size while still maintaining its effectiveness. This method will decompose the task into three phases: (i) serial cyclic spatial relationship modeling of the pose; (ii) parallel cyclic temporal relationship modeling of the pose; and (iii) summarization of multiple features and synthesis of the final 3D pose after linear regression. With the three main processes mentioned above, the final predicted 3D poses are not only improved compared to traditional methods but also more accurate in terms of precision. After experimental validation, Recurrent Transformer achieves leading results on Human3.6M.

Due to the underdeveloped scanning technology, some old movie films are scanned in digital format with lower resolution, which does not meet the viewing needs of contemporary viewers. Therefore, it is necessary to superresolution processing them to improve the image quality. However, some old movies will appear blurred after scanning. In this case, the existing algorithm super-resolution reconstruction results are often not ideal. This paper adds image deblurring pre-processing before the super-resolution processing. First, the old movie is deblurred according to the deblurring generation training model against the network, and then the image is super-resolution processed by the sub-pixel convolution network. The method aims to improve the problem that the repair effect caused by the image blur caused by the old film in the super-resolution reconstruction is not ideal.