In recent years, while generative AI has advanced significantly in image generation, video generation continues to face challenges in controllability, length, and detail quality, which hinder its application. We present MimicMotion, a framework for generating high-quality human videos of arbitrary length using motion guidance. Our approach has several highlights. Firstly, we introduce confidence-aware pose guidance that ensures high frame quality and temporal smoothness. Secondly, we introduce regional loss amplification based on pose confidence, which reduces image distortion in key regions. Lastly, we propose a progressive latent fusion strategy to generate long and smooth videos. Experiments demonstrate the effectiveness of our approach in producing high-quality human motion videos. Videos and comparisons are available at https://tencent.github.io/MimicMotion.

Student recognition in smart classrooms is challenging due to low resolution, occlusions, and various face orientations. We propose a video-based approach for robust face recognition. It firstly collects a continuous sequence of face images through inter-frame analysis. Then, it aggregates face features, via statistical elimination of outliers. We introduce a new consistency loss to address varying face resolutions, enabling the learning of scale-robust features. Experimental results demonstrate that our proposed approach improves recognition performance under various conditions compared to previous methods. In our experiments, it achieved the highest recognition accuracy (83.57%) for 8×8 resolution cases.

Darkness brings us uncertainty, worry and low confidence. This is a problem not only applicable to us walking in a dark evening but also for drivers driving a car on the road with very dim or even without lighting condition. To address this problem, we propose a new CNN structure named as Video Lightening Network (VLN) that regards the low-light enhancement as a residual learning task, which is useful as reference to indirectly lightening the environment, or for vision-based application systems, such as driving assistant systems. The VLN consists of several Lightening Back-Projection (LBP) and Temporal Aggregation (TA) blocks. Each LBP block enhances the low-light frame by domain transfer learning that iteratively maps the frame between the low- and normal-light domains. A TA block handles the motion among neighboring frames by investigating the spatial and temporal relationships. Several TAs work in a multi-scale way, which compensates the motions at different levels. The proposed architecture has a consistent enhancement for different levels of illuminations, which significantly increases the visual quality even in the extremely dark environment. Extensive experimental results show that the proposed approach outperforms other methods under both objective and subjective metrics.

We propose a Deep Lightening Network (DLN) for low-light image enhancement. Inspire by the domain transfer study, we propose a novel cycle learning structure to learn the mapping relationship between low- and normal-light images. Each DLN consists of several Lightening Back-Projection (LBP) blocks that learn the residual between low- and normal-light images. To efficiently estimate the local and global information, we fuse the features from different LBP results. Experimental results on different datasets show that our proposed DLN approach outperforms other approaches in all objective and subjective measures.

3D ultrasound imaging shows great promise for scoliosis diagnosis thanks to its low-costing, radiation-free and real-time characteristics. The key to accessing scoliosis by ultrasound imaging is to accurately segment the bone area and measure the scoliosis degree based on the symmetry of the bone features. The ultrasound images tend to contain many speckles and regular occlusion noise which is difficult, tedious and time-consuming for experts to find out the bony feature. In this paper, we propose a robust bone feature segmentation method based on the U-net structure for ultrasound spine Volume Projection Imaging (VPI) images. The proposed segmentation method introduces a total variance loss to reduce the sensitivity of the model to small-scale and regular occlusion noise. The proposed approach improves 2.3% of Dice score and 1% of AUC score as compared with the u-net model and shows high robustness to speckle and regular occlusion noise.

Low-light image enhancement is a challenging task that has attracted considerable attention. Pictures taken in low-light conditions often have bad visual quality. To address the problem, we regard the low-light enhancement as a residual learning problem that is to estimate the residual between low- and normal-light images. In this paper, we propose a novel Deep Lightening Network (DLN) that benefits from the recent development of Convolutional Neural Networks (CNNs). The proposed DLN consists of several Lightening Back-Projection (LBP) blocks. The LBPs perform lightening and darkening processes iteratively to learn the residual for normal-light estimations. To effectively utilize the local and global features, we also propose a Feature Aggregation (FA) block that adaptively fuses the results of different LBPs. We evaluate the proposed method on different datasets. Numerical results show that our proposed DLN approach outperforms other methods under both objective and subjective metrics.