The limited research on 3D animal pose estimation is attributed to data scarcity and perspective ambiguities, despite its significant applications in various fields including biology, medicine, and animation. To resolve data scarcity, we put forward an unsupervised method for estimating 3D animal pose with only 2D pose available alone. To overcome perspective ambiguities, we propose canonical pose, camera, and view consistency losses to represent geometric consistency constraints for self-supervised learning. Specifically, the input 2D pose is fed into the pose generator network and camera network, and then regressed to the 3D canonical pose and camera rotation, respectively. In the training phase, the regressed 3D canonical pose is subjected to random re-projection to synthesize new 2D poses, which are also decomposed into 3D canonical pose and camera rotation to form geometric consistency constraints. Experimental results demonstrate that the proposed method achieves the best performance in unsupervised monocular 3D animal pose estimation. The corresponding code is available at: https://github.com/maicao2018/GeoSelfPose. © 2025 Elsevier Ltd

Automated face recognition systems are vulnerable against various attacks, such as adversarial attacks, digital manipulation and physical spoofs. As a special case of digital manipulation attacks, face morphing draws increasing concerns due to such attacks generalizing well across diverse face recognition systems. However, the threat of face morphing attacks is underestimated due to the following characteristics of state-of-the-art morphing methods. (i) Their generated face images have low visual quality with artifacts, (ii) they fail to guarantee high similarity with contributing subjects, and (iii) they do not explicitly consider countering face morphing detection methods when constructing morphing attacks. Based on the observation that facial geometry information is vital in face recognition, we present in this paper a geometry-aware generative model (GAGM), which can realize more threatening attacks against human experts, face recognition and morphing attack detection. GAGM synthesizes morphs with the drive of both facial geometry and texture based on dual invertible networks, resulting in visually realistic and highly deceptive morphed face images. To circumvent morphing-attack detection, GAGM implements a fine-grained adversarial attack strategy to mislead the detection methods. Visualization results demonstrate that GAGM, compared to existing techniques, is capable of generating visually faultless facial morphs. Meanwhile, extensive quantitative experiments show that GAGM can significantly increase the attack success rate against face recognition and deceive various morphing attack detection models. © 2025 Elsevier B.V.

目的 低质量3维人脸识别是近年来模式识别领域的热点问题；区别于传统高质量3维人脸识别，低质量、高噪声是低质量3维人脸识别面对的主要问题。围绕低质量3维人脸数据噪声大、依赖单张有限深度数据提取有效特征困难的问题，提出了一种联合软阈值去噪和视频数据融合的低质量3维人脸识别方法。方法 首先，针对低质量3维人脸中存在的噪声问题，提出了一个即插即用的软阈值去噪模块，在网络提取特征的过程中对特征进行去噪处理。为了使网络提取的特征更具有判别性，结合softmax和Arcface（additive angular margin loss for deep face recognition）提出的联合渐变损失函数使网络提取更具有判别性特征。为了更好地利用多帧低质量视频数据实现人脸数据质量提升，提出了基于门控循环单元的视频数据融合模块，实现了视频帧数据间互补信息的有效融合，进一步提高了低质量3维人脸识别准确率。结果 实验在两个公开数据集上与较新方法进行比较，在Lock3DFace（low-cost kinect 3D faces）开、闭集评估协议上，相比于性能第2的方法，平均识别率分别提高了0.28%和3.13%；在ExtendedMulti-Dim开集评估协议上，相比于性能第2的方法，平均识别率提高了1.03%。结论 提出的低质量3维人脸识别方法，不仅能有效缓解低质量噪声带来的影响，还有效融合了多帧视频数据的互补信息，大幅提高了低质量3维人脸识别准确率。

为了生成更准确流畅的虚拟人动画,采用Kinect设备捕获三维人体姿态数据的同时,使用单目人体三维姿态估计算法对Kinect的彩色信息进行骨骼点数据推理,从而实时优化人体姿态估计效果,并驱动虚拟人物模型生成动画。首先,提出了一种时空优

Salient object detection(SOD)is a long-standing research topic in computer vision with increasing interest in the past decade.Since light fields record comprehensive information of natural scenes that benefit SOD in a

Existing RGB-D salient object detection (SOD) models usually treat RGB and depth as independent information and design separate networks for feature extraction from each. Such schemes can easily be constrained by a limited amount of training data or over-reliance on an elaborately designed training process. Inspired by the observation that RGB and depth modalities actually present certain commonality in distinguishing salient objects, a novel joint learning and densely cooperative fusion (JL-DCF) architecture is designed to learn from both RGB and depth inputs through a shared network backbone, known as the Siamese architecture. In this paper, we propose two effective components: joint learning (JL), and densely cooperative fusion (DCF). The JL module provides robust saliency feature learning by exploiting cross-modal commonality via a Siamese network, while the DCF module is introduced for complementary feature discovery. Comprehensive experiments using five popular metrics show that the designed framework yields a robust RGB-D saliency detector with good generalization. As a result, JL-DCF significantly advances the state-of-the-art models by an average of similar to 2.0% (max F-measure) across seven challenging datasets. In addition, we show that JL-DCF is readily applicable to other related multi-modal detection tasks, including RGB-T (thermal infrared) SOD and video SOD, achieving comparable or even better performance against state-of-the-art methods. We also link JL-DCF to the RGB-D semantic segmentation field, showing its capability of outperforming several semantic segmentation models on the task of RGB-D SOD. These facts further confirm that the proposed framework could offer a potential solution for various applications and provide more insight into the cross-modal complementarity task.

Salient object detection (SOD) is a long-standing research topic in computer vision with increasing interest in the past decade. Since light fields record comprehensive information of natural scenes that benefit SOD in a number of ways, using light field inputs to improve saliency detection over conventional RGB inputs is an emerging trend. This paper provides the first comprehensive review and a benchmark for light field SOD, which has long been lacking in the saliency community. Firstly, we introduce light fields, including theory and data forms, and then review existing studies on light field SOD, covering ten traditional models, seven deep learning-based models, a comparative study, and a brief review. Existing datasets for light field SOD are also summarized. Secondly, we benchmark nine representative light field SOD models together with several cutting-edge RGB-D SOD models on four widely used light field datasets, providing insightful discussions and analyses, including a comparison between light field SOD and RGB-D SOD models. Due to the inconsistency of current datasets, we further generate complete data and supplement focal stacks, depth maps, and multi-view images for them, making them consistent and uniform. Our supplemental data make a universal benchmark possible. Lastly, light field SOD is a specialised problem, because of its diverse data representations and high dependency on acquisition hardware, so it differs greatly from other saliency detection tasks. We provide nine observations on challenges and future directions, and outline several open issues. All the materials including models, datasets, benchmarking results, and supplemented light field datasets are publicly available at https://github.com/kerenfu/LFSOD-Survey. [Figure not available: see fulltext.]. © 2022, The Author(s).

随着生成对抗网络在图像生成领域的发展,人脸表情图像生成效果有了显著提升。然而,目前方法往往基于传统表情分类,忽略表情的复杂多样性。然而针对生成多样表情的数据库数据规模较小。为了解决这一问题,提出引入标记分布的人脸表情生成方法。方法在数据量较少的情况下,以标签分布对表情标签进行处理,基于生成对抗网络实现人脸表情图像生成,并在Oulu-CASIA数据库和CFEED数据库上对该方法进行验证。