检索结果-内蒙古大学图书馆

KV Inversion: KV Embeddings Learning for Text-Conditioned Real Image Action Editing

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Jiancheng Liu, Yifan Qin, Jin Chen, Shifeng ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China University of Chinese Academy of Sciences Beijing China

Text-conditioned image editing is a recently emerged and highly practical task, and its potential is immeasurable. However, most of the concurrent methods are unable to perform action editing, i.e. they can not produce results that conform to the action semantics of the editing prompt and preserve the content of the original image. To solve the problem of action editing, we propose KV Inversion, a method that can achieve satisfactory reconstruction performance and action editing, which can solve two major problems: 1) the edited result can match the corresponding action, and 2) the edited object can retain the texture and identity of the original real image. In addition, our method does not require training the Stable Diffusion model itself, nor does it require scanning a large-scale dataset to perform time-consuming training. Copyright © 2023, The Authors. All rights reserved.

关键词： Textures

Bootstrap Diffusion Model Curve Estimation for High Resolution Low-Light Image Enhancement

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Jiancheng Liu, Yifan Chen, Shifeng ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China University of Chinese Academy of Sciences Beijing China

Learning-based methods have attracted a lot of research attention and led to significant improvements in low-light image enhancement. However, most of them still suffer from two main problems: expensive computational cost in high resolution images and unsatisfactory performance in simultaneous enhancement and denoising. To address these problems, we propose BDCE, a bootstrap diffusion model that exploits the learning of the distribution of the curve parameters instead of the normal-light image itself. Specifically, we adopt the curve estimation method to handle the high-resolution images, where the curve parameters are estimated by our bootstrap diffusion model. In addition, a denoise module is applied in each iteration of curve adjustment to denoise the intermediate enhanced result of each iteration. We evaluate BDCE on commonly used benchmark datasets, and extensive experiments show that it achieves state-of-the-art qualitative and quantitative performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

Complex 3D General Object Reconstruction from Line Drawings

学校读者我要写书评

暂无评论

Complex 3D General Object Reconstruction from Line Drawings

International Conference on computer vision (ICCV)

作者： Linjie Yang Jianzhuang Liu Xiaoou Tang Department of Information Engineering Chinese University of Hong Kong Shenzhen Key Lab of Computer Vision and Pattern Recognition Chinese Academy of Sciences China

ISBN: (纸本)9781479928415

An important topic in computer vision is 3D object reconstruction from line drawings. Previous algorithms either deal with simple general objects or are limited to only manifolds (a subset of solids). In this paper, we propose a novel approach to 3D reconstruction of complex general objects, including manifolds, non-manifold solids, and nonsolids. Through developing some 3D object properties, we use the degree of freedom of objects to decompose a complex line drawing into multiple simpler line drawings that represent meaningful building blocks of a complex object. After 3D objects are reconstructed from the decomposed line drawings, they are merged to form a complex object from their touching faces, edges, and vertices. Our experiments show a number of reconstruction examples from both complex line drawings and images with line drawings superimposed. Comparisons are also given to indicate that our algorithm can deal with much more complex line drawings of general objects than previous algorithms.

关键词： Solids Three-dimensional displays Manifolds Image reconstruction computer vision Search problems Image edge detection

Dynamic Feature Queue for Surveillance Face Anti-spoofing via Progressive Training

学校读者我要写书评

暂无评论

Dynamic Feature Queue for Surveillance Face Anti-spoofing vi...

IEEE computer Society Conference on computer vision and pattern recognition Workshops (CVPRW)

作者： keyao Wang Mouxiao Huang Guosheng Zhang Haixiao Yue Gang Zhang Yu Qiao Department of Computer Vision Technology (VIS) Baidu Inc. ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences

In recent years, face recognition systems have faced increasingly security threats, making it essential to employ Face Anti-spoofing (FAS) to protect against various types of attacks in traditional scenarios like phone unlocking, face payment and self-service security inspection. However, further exploration is required to fully secure FAS in long-distance settings. In this paper, we propose two contributions to enhance the security of face recognition systems: Dynamic Feature Queue (DFQ) and Progressive Training Strategy (PTS). DFQ converts the conventional binary classification task into a multi-classification task. It treats live samples as a closed set and attack samples as an open set by using a dynamic queue that stores the features of spoofing samples and updates them. On the other hand, PTS targets difficult samples and iteratively adds them in batches for training. The proposed PTS divides the entire training set into blocks, trains only a small portion of the data, and gradually increases the training data with each stage while also incorporating low-scoring positive samples and high-scoring spoof samples from the test set. These two contributions complement each other by enhancing the model’s ability to generalize and defend against various types of attacks, making the face recognition system more secure and reliable. Our proposed methods have achieved top performance on ACER metric with 4.73% on the SuHiFiMask dataset [11] and won the first prize in Surveillance Face Anti-spoofing track of the Challenge@CVPR 2023.

关键词：

A Maximum Entropy Feature Descriptor for Age Invariant Face recognition

学校读者我要写书评

暂无评论

A Maximum Entropy Feature Descriptor for Age Invariant Face ...

IEEE Conference on computer vision and pattern recognition

作者： Dihong Gong Zhifeng Li Dacheng Tao Jianzhuang Liu Xuelong Li Shenzhen Key Lab. of Comput. Vision & Pattern Recognition Shenzhen Inst. of Adv. Technol. Shenzhen China

ISBN: (纸本)9781467369657

In this paper, we propose a new approach to overcome the representation and matching problems in age invariant face recognition. First, a new maximum entropy feature descriptor (MEFD) is developed that encodes the microstructure of facial images into a set of discrete codes in terms of maximum entropy. By densely sampling the encoded face image, sufficient discriminatory and expressive information can be extracted for further analysis. A new matching method is also developed, called identity factor analysis (IFA), to estimate the probability that two faces have the same underlying identity. The effectiveness of the framework is confirmed by extensive experimentation on two face aging datasets, MORPH (the largest public-domain face aging dataset) and FGNET. We also conduct experiments on the famous LFW dataset to demonstrate the excellent generalizability of our new approach.

关键词： Maximum entropy Mug shots Facial recognition Face Dataset Invariant Descriptors Face

Frame attention networks for facial expression recognition in videos

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Meng, Debin Peng, Xiaojiang Wang, Kai Qiao, Yu Shenzhen Institutes of Advanced Technology Chinese Academy of Science Shenzhen China Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen China University of Chinese Academy of Sciences Beijing China

The video-based facial expression recognition aims to classify a given video into several basic emotions. How to integrate facial features of individual frames is crucial for this task. In this paper, we propose the Frame Attention Networks (FAN)1, to automatically highlight some discriminative frames in an end-to-end framework. The network takes a video with a variable number of face images as its input and produces a fixed-dimension representation. The whole network is composed of two modules. The feature embedding module is a deep Convolutional Neural Network (CNN) which embeds face images into feature vectors. The frame attention module learns multiple attention weights which are used to adaptively aggregate the feature vectors to form a single discriminative video representation. We conduct extensive experiments on CK+ and AFEW8.0 datasets. Our proposed FAN shows superior performance compared to other CNN based methods and achieves state-of-the-art performance on CK+. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

RankSRGAN: Super resolution generative adversarial networks with learning to rank

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Wenlong Liu, Yihao Dong, Chao Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Shanghai AI Lab Shanghai China

Generative Adversarial Networks (GAN) have demonstrated the potential to recover realistic details for single image super-resolution (SISR). To further improve the visual quality of super-resolved results, PIRM2018-SR Challenge employed perceptual metrics to assess the perceptual quality, such as PI, NIQE, and Ma. However, existing methods cannot directly optimize these indifferentiable perceptual metrics, which are shown to be highly correlated with human ratings. To address the problem, we propose Super-Resolution Generative Adversarial Networks with Ranker (RankSRGAN) to optimize generator in the direction of different perceptual metrics. Specifically, we first train a Ranker which can learn the behaviour of perceptual metrics and then introduce a novel rank-content loss to optimize the perceptual quality. The most appealing part is that the proposed method can combine the strengths of different SR methods to generate better results. Furthermore, we extend our method to multiple Rankers to provide multi-dimension constraints for the generator. Extensive experiments show that RankSRGAN achieves visually pleasing results and reaches state-of-the-art performance in perceptual metrics and quality. Project page: https://***/Projects/RankSRGAN. © 2021, CC BY.

关键词： Generative adversarial networks

Saliency attention based abnormal event detection in video

学校读者我要写书评

暂无评论

Saliency attention based abnormal event detection in video

IEEE International Conference on Robotics and Biomimetics

作者： Wang Huan Huiwen Guo Xinyu Wu Shenzhen Key Lab for Computer Vision and Pattern Recognition University of Chinese Academy of Sicences Department of Mechanical and Automation Engineering The Chinese University of Hong Kong

ISBN: (纸本)9781479973989

Most existing methods for abnormal event detection in the literature are relied on a training phase. Different from conventional approaches for abnormal event detection, a saliency attention based abnormal event detection approach is proposed in this paper. It is inspired by the visual attention mechanism that abnormal events are those which attract attention mostly in videos. The temporal and spatial abnormal saliency maps are firstly constructed and then the final abnormal event map is formatted by fusing them using a method with dynamic coefficients. The temporal abnormal saliency map is constructed by motion contrast between keypoints extracted from two successive video frames. The spatial abnormal saliency map is structured based on the color contrasts. Experiments performed on the benchmark datasets show that the proposed method achieves a high accurate and robust results for abnormal event detection without a training phase.

关键词： Clustering algorithms Hidden Markov models Event detection Conferences Color computer vision pattern recognition

RankSRGAN: Generative Adversarial Networks With Ranker for Image Super-Resolution

学校读者我要写书评

暂无评论

RankSRGAN: Generative Adversarial Networks With Ranker for I...

International Conference on computer vision (ICCV)

作者： Wenlong Zhang Yihao Liu Chao Dong Yu Qiao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

Generative Adversarial Networks (GAN) have demonstrated the potential to recover realistic details for single image super-resolution (SISR). To further improve the visual quality of super-resolved results, PIRM2018-SR Challenge employed perceptual metrics to assess the perceptual quality, such as PI, NIQE, and Ma. However, existing methods cannot directly optimize these indifferentiable perceptual metrics, which are shown to be highly correlated with human ratings. To address the problem, we propose Super-Resolution Generative Adversarial Networks with Ranker (RankSRGAN) to optimize generator in the direction of perceptual metrics. Specifically, we first train a Ranker which can learn the behavior of perceptual metrics and then introduce a novel rank-content loss to optimize the perceptual quality. The most appealing part is that the proposed method can combine the strengths of different SR methods to generate better results. Extensive experiments show that RankSRGAN achieves visually pleasing results and reaches state-of-the-art performance in perceptual metrics. Project page: https://***/Projects/RankSRGAN.

关键词： Measurement Image resolution Feature extraction Gallium nitride Generators Visualization Image quality