检索结果-内蒙古大学图书馆

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024, CC BY.

关键词： Color image processing

Learning Context-Based Non-local Entropy Modeling for Image Compression

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Timofte, Radu Zhang, David Zuo, Wangmeng Zhang, Kai Li, Mu School of Science and Engineering Chinese University of Hong Kong ShenzhenGuangdong518172 China Computer Vision Laboratory ETH Zurich Zurich Switzerland School of Computer Science and Technology Harbin Institute of Technology Harbin150001 China Shenzhen Research Institute of Big Data Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

The entropy of the codes usually serves as the rate loss in the recent learned lossy image compression methods. Precise estimation of the probabilistic distribution of the codes plays a vital role in the performance. However, existing deep learning based entropy modeling methods generally assume the latent codes are statistically independent or depend on some side information or local context, which fails to take the global similarity within the context into account and thus hinder the accurate entropy estimation. To address this issue, we propose a non-local operation for context modeling by employing the global similarity within the context. Specifically, we first introduce the proxy similarity functions and spatial masks to handle the missing reference problem in context modeling. Then, we combine the local and the global context via a non-local attention block and employ it in masked convolutional networks for entropy modeling. The entropy model is further adopted as the rate loss in a joint rate-distortion optimization to guide the training of the analysis transform and the synthesis transform network in transforming coding framework. Considering that the width of the transforms is essential in training low distortion models, we finally produce an U-Net block in the transforms to increase the width with manageable memory consumption and time complexity. Experiments on Kodak and Tecnick datasets demonstrate the superiority of the proposed context-based non-local attention block in entropy modeling and the U-Net block in low distortion compression against the existing image compression standards and recent deep image compression models. Copyright © 2020, The Authors. All rights reserved.

关键词： Image compression

Research on Neural Networks Integration for Object Classification in Video Analysis Systems

学校读者我要写书评

暂无评论

Research on Neural Networks Integration for Object Classific...

International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM)

作者： Ivan Fomin Vladislav Burin Aleksandr Bakhshiev Computer vision lab Russian State Scientific Center for Robotics and Technical Cybernetics Saint-Petersburg Russia Institute of Metallurgy Mechanical Engineering and Transport Peter the Great St.Petersburg Polytechnic University Saint-Petersburg Russia

ISBN: (数字)9781728145907

ISBN: (纸本)9781728145914

Object recognition with the help of outdoor video surveillance cameras is an important task in the context of ensuring the security at enterprises, public places and even private premises. There have long existed systems that allow detecting moving objects in the image sequence from a video surveillance system. Such a system is partially considered in this research. It detects moving objects using a background model, which has certain problems. Due to this some objects are missed or detected falsely. We propose to combine the moving objects detection results with the classification, using a deep neural network. This will allow determining whether a detected object belongs to a certain class, sorting out false detections, discarding the unnecessary ones (sometimes individual classes are unwanted), to divide detected people into the employees in the uniform and all others, etc. The authors perform a network training in the Keras developer-friendly environment that provides for quick building, changing and training of network architectures. The performance of the Keras integration into a video analysis system, using direct Python script execution techniques, is between 6 and 52 ms, while the precision is between 59.1% and 97.2% for different architectures. The integration, made by freezing a selected network architecture with weights, is selected after testing. After that, frozen architecture can be imported into video analysis using the TensorFlow interface for C++. The performance of such type of integration is between 3 and 49 ms. The precision is between 63.4% and 97.8% for different architectures.

关键词：

Attention-driven dynamic graph convolutional network for multi-label image recognition

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ye, Jin He, Junjun Peng, Xiaojiang Wu, Wenhao Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China School of Biomedical Engineering Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China

Recent studies often exploit Graph Convolutional Network (GCN) to model label dependencies to improve recognition accuracy for multi-label image recognition. However, constructing a graph by counting the label co-occurrence possibilities of the training data may degrade model generalizability, especially when there exist occasional co-occurrence objects in test images. Our goal is to eliminate such bias and enhance the robustness of the learnt features. To this end, we propose an Attention-Driven Dynamic Graph Convolutional Network (ADD-GCN) to dynamically generate a specific graph for each image. ADD-GCN adopts a Dynamic Graph Convolutional Network (D-GCN) to model the relation of content-aware category representations that are generated by a Semantic Attention Module (SAM). Extensive experiments on public multi-label benchmarks demonstrate the effectiveness of our method, which achieves mAPs of 85.2%, 96.0%, and 95.5% on MS-COCO, VOC2007, and VOC2012, respectively, and outperforms current state-of-the-art methods with a clear margin. All codes can be found at https://***/Yejin0111/ADD-GCN. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

TextTopicNet - Self-supervised learning of visual features through embedding images on semantic text spaces

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Patel, Yash Gomez, Lluis Gomez, Raul Rusiñol, Marçal Karatzas, Dimosthenis Jawahar, C.V. Robotics Institute Carnegie Mellon University PA United States CVIT KCIS IIIT Hyderabad India Computer Vision Center Universitat Autonoma de Barcelona Spain Eurecat Centre Tecnolgic de Catalunya Barcelona Spain

The immense success of deep learning based methods in computer vision heavily relies on large scale training datasets. These richly annotated datasets help the network learn discriminative visual features. Collecting and annotating such datasets requires a tremendous amount of human effort and annotations are limited to popular set of classes. As an alternative, learning visual features by designing auxiliary tasks which make use of freely available self-supervision has become increasingly popular in the computer vision community. In this paper, we put forward an idea to take advantage of multi-modal context to provide self-supervision for the training of computer vision algorithms. We show that adequate visual features can be learned efficiently by training a CNN to predict the semantic textual context in which a particular image is more probable to appear as an illustration. More specifically we use popular text embedding techniques to provide the self-supervision for the training of deep CNN. Our experiments demonstrate state-of-the-art performance in image classification, object detection, and multi-modal retrieval compared to recent self-supervised or naturally-supervised approaches. Copyright © 2018, The Authors. All rights reserved.

关键词： Semantics

UniTSFace: unified threshold integrated sample-to-sample loss for face recognition 23

学校读者我要写书评

暂无评论

UniTSFace: unified threshold integrated sample-to-sample los...

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Qiufu Li Xi Jia Jiancan Zhou Linlin Shen Jinming Duan National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China and Computer Vision Institute Shenzhen University China and SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China and Computer Vision Institute Shenzhen University China and School of Computer Science University of Birmingham UK National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China and Computer Vision Institute Shenzhen University China and Aqara Lumi United Technology Co. Ltd China School of Computer Science University of Birmingham UK and Alan Turing Institute UK

Sample-to-class-based face recognition models can not fully explore the cross-sample relationship among large amounts of facial images, while sample-to-sample-based models require sophisticated pairing processes for training. Furthermore, neither method satisfies the requirements of real-world face verification applications, which expect a unified threshold separating positive from negative facial pairs. In this paper, we propose a unified threshold integrated sample-to-sample based loss (USS loss), which features an explicit unified threshold for distinguishing positive from negative pairs. Inspired by our USS loss, we also derive the sample-to-sample based softmax and BCE losses, and discuss their relationship. Extensive evaluation on multiple benchmark datasets, including MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace, demonstrates that the proposed USS loss is highly efficient and can work seamlessly with sample-to-class-based losses. The embedded loss (USS and sample-to-class Softmax loss) overcomes the pitfalls of previous approaches and the trained facial model UniTSFace exhibits exceptional performance, outperforming state-of-the-art methods, such as CosFace, ArcFace, VPL, AnchorFace, and UNPG. Our code is available at https://***/CVI-SZU/UniTSFace.

关键词：

Scalable temporal interest points for abstraction and classification of video events

学校读者我要写书评

暂无评论

Scalable temporal interest points for abstraction and classi...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Seung-Hoon Han ln-So Kweon Digital Media R&D Center Samsung Electronics Company Limited South Korea Robotics and Computer Vision Laboratory Division of Electrical Engineering Department of EECS Korea Advanced Institute of Science and Technology South Korea

The image sequence of a static scene includes similar or redundant information over time. Hence, motion-discontinuous instants can efficiently characterize a video shot or event. However, such instants (key frames) are differently identified according to the change of velocity and acceleration of motion, and such scales of change might be different on each sequence of the same event. In this paper, we present a scalable video abstraction in which the key frames are obtained by the maximum curvature of camera motion at each temporal scale. The scalability means dealing with the velocity and acceleration change of motion. In the temporal neighborhood determined by the scale, the scene features (motion, color, and edge) can be used to index and classify the video events. Therefore, those key frames provide temporal interest points (TIPs) for the abstraction and classification of video events.

关键词： Layout Acceleration Cameras Humans Research and development Robot vision systems computer vision Laboratories Image sequences Scalability

Calibrated and partially calibrated semi-generalized homographies

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Bhayani, Snehal Sattler, Torsten Barath, Daniel Beliansky, Patrik Heikkilä, Janne Kukelova, Zuzana Center for Machine Vision and Signal Analysis University of Oulu Finland Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Computer Vision and Geometry Group Department of Computer Science ETH Zürich Faculty of Mathematics and Physics Charles University Prague Czech Republic Visual Recognition Group Faculty of Electrical Engineering Czech Technical University in Prague

In this paper, we propose the first minimal solutions for estimating the semi-generalized homography given a perspective and a generalized camera. The proposed solvers use five 2D-2D image point correspondences induced by a scene plane. One group of solvers assumes the perspective camera to be fully calibrated, while the other estimates the unknown focal length together with the absolute pose parameters. This setup is particularly important in structurefrom-motion and visual localization pipelines, where a new camera is localized in each step with respect to a set of known cameras and 2D-3D correspondences might not be available. Thanks to a clever parametrization and the elimination ideal method, our solvers only need to solve a univariate polynomial of degree five or three, respectively a system of polynomial equations in two variables. All proposed solvers are stable and efficient as demonstrated by a number of synthetic and real-world experiments. Copyright © 2021, The Authors. All rights reserved.

关键词： Cameras

Exploiting Aggregation and Segregation of Representations for Domain Adaptive Human Pose Estimation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Peng, Qucheng Zheng, Ce Ding, Zhengming Wang, Pu Chen, Chen Center for Research in Computer Vision University of Central Florida Orlando United States Robotics Institute Carnegie Mellon University Pittsburgh United States Department of Computer Science Tulane University New Orleans United States University of North Carolina at Charlotte Charlotte United States

Human pose estimation (HPE) has received increasing attention recently due to its wide application in motion analysis, virtual reality, healthcare, etc. However, it suffers from the lack of labeled diverse real-world datasets due to the time- and labor-intensive annotation. To cope with the label deficiency issue, one common solution is to train the HPE models with easily available synthetic datasets (source) and apply them to real-world data (target) through domain adaptation (DA). Unfortunately, prevailing domain adaptation techniques within the HPE domain remain predominantly fixated on effecting alignment and aggregation between source and target features, often sidestepping the crucial task of excluding domain-specific representations. To rectify this, we introduce a novel framework that capitalizes on both representation aggregation and segregation for domain adaptive human pose estimation. Within this framework, we address the network architecture aspect by disentangling representations into distinct domain-invariant and domain-specific components, facilitating aggregation of domain-invariant features while simultaneously segregating domain-specific ones. Moreover, we tackle the discrepancy measurement facet by delving into various keypoint relationships and applying separate aggregation or segregation mechanisms to enhance alignment. Extensive experiments on various benchmarks, e.g., Human3.6M, LSP, H3D, and FreiHand, show that our method consistently achieves state-of-the-art performance. The project is available at https: //***/davidpengucf/EPIC. © 2024, CC BY.

关键词： Virtual reality