Pattern Recognition and Computer Vision [[electronic resource] ] : 6th Chinese Conference, PRCV 2023, Xiamen, China, October 13–15, 2023, Proceedings, Part XI / / edited by Qingshan Liu, Hanzi Wang, Zhanyu Ma, Weishi Zheng, Hongbin Zha, Xilin Chen, Liang Wang, Rongrong Ji

• Pubblicazione: Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
• Edizione: 1st ed. 2024.
• Descrizione fisica: 1 online resource (XIV, 521 p. 207 illus., 202 illus. in color.)
• Disciplina: 006
• Soggetto topico: Image processing - Digital techniques; Computer vision; Artificial intelligence; Application software; Computer networks; Computer systems; Machine learning; Computer Imaging, Vision, Pattern Recognition and Graphics; Artificial Intelligence; Computer and Information Systems Applications; Computer Communication Networks; Computer System Implementation; Machine Learning
• Persona (resp. second.): LiuQingshan; WangHanzi; MaZhanyu; ZhengWeishi; ZhaHongbin; ChenXilin; WangLiang; JiRongrong
• Nota di contenuto: Intro -- Preface -- Organization -- Contents - Part XI -- Low-Level Vision and Image Processing -- Efficiently Amalgamated CNN-Transformer Network for Image Super-Resolution Reconstruction -- 1 Introduction -- 2 Related Work -- 2.1 CNN for SISR -- 2.2 Lightweight SISR -- 3 Method Overview -- 3.1 The Fundamentals of SISR -- 3.2 Network Structure -- 4 Experimental Results and Analysis -- 4.1 Training Details and Evaluation Metrics -- 4.2 Experimental Results and Analysis -- 5 Conclusion -- References -- A Hybrid Model for Video Compression Based on the Fusion of Feature Compression Framework and Multi-object Tracking Network -- 1 Introduction -- 2 Related Works -- 2.1 JDE (Joint Detection and Embedding Model) -- 2.2 DCT (Discrete Cosine Transform) Method -- 3 Methodology -- 3.1 Feature Extractor -- 3.2 Feature Reconstructor -- 3.3 Feature Encoder and Decoder -- 4 Experiment -- 4.1 The Architecture of the Hybrid Model -- 4.2 Training Details -- 4.3 Evaluation Results -- 5 Conclusions -- References -- Robust Degradation Representation via Efficient Diffusion Model for Blind Super-Resolution -- 1 Introduction -- 2 Related Work -- 3 Methods -- 3.1 Lightweight Degradation Extractor (LDE) -- 3.2 Degradation-Aware Transformer (DAT) -- 3.3 Diffusion Model Training and Inference -- 4 Experiments -- 4.1 Training and Testing Datasets -- 4.2 Implementation and Training Details -- 4.3 Comparison with Existing Blind SR Methods -- 4.4 Ablation Study -- 5 Conclusion -- References -- MemDNet: Memorizing More Exogenous Information to Dehaze Natural Hazy Image -- 1 Introduction -- 2 Proposed Method -- 2.1 Dense Block -- 2.2 Enhanced Block -- 2.3 Memory Branch -- 3 Experiments -- 3.1 Experimental Settings -- 3.2 Comparison with SOTAs -- 3.3 Ablation Study -- 4 Conclusion -- References -- Technical Quality-Assisted Image Aesthetics Quality Assessment -- 1 Introduction. ; 2 Related Work -- 2.1 Technical Quality Assessment -- 2.2 Aesthetic Quality Assessment -- 3 Proposed Method -- 3.1 Theme-Aware Aesthetic Feature Extraction -- 3.2 Technical Quality Feature Extraction -- 3.3 Feature Fusion and Aesthetic Prediction -- 4 Experimental Results -- 4.1 Databases and Settings -- 4.2 Comparison with the State-of-the-Arts -- 4.3 Ablation Experiments -- 5 Conclusion -- References -- Self-supervised Low-Light Image Enhancement via Histogram Equalization Prior -- 1 Introduction -- 2 Methodology -- 2.1 Histogram Equalization Prior -- 2.2 Architecture -- 2.3 Loss Function -- 3 Experimental Validation -- 3.1 Implementation Details -- 3.2 Quantitative Evaluation -- 3.3 Qualitative Evaluation -- 3.4 Generalization Ability on Real-World Images -- 4 Ablation Studies -- 4.1 Comparison with Other Prior Information -- 4.2 The Effectiveness of Histogram Equalization Prior Loss -- 5 Conclusions -- References -- Enhancing GAN Compression by Image Probability Distribution Distillation -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Background -- 3.2 Image Probability Distribution Distillation -- 3.3 Asynchronous Weighted Discriminator -- 4 Experimentation -- 4.1 Experimental Settings -- 4.2 Result Comparison -- 4.3 Ablation Study -- 5 Conclusion -- References -- HDTR-Net: A Real-Time High-Definition Teeth Restoration Network for Arbitrary Talking Face Generation Methods -- 1 Introduction -- 2 Related Work -- 2.1 Talking Face Generation -- 2.2 Face Restoration -- 3 Method -- 3.1 Fine-Grained Feature Fusion -- 3.2 Decoder -- 3.3 Loss Function -- 4 Experiment -- 4.1 Experimental Settings -- 4.2 Experimental Results -- 4.3 Ablation Study -- 5 Conclusion -- References -- Multi-stream-Based Low-Latency Viewport Switching Scheme for Panoramic Videos -- 1 Introduction -- 2 Related Works -- 2.1 Tile-Based Viewport Adaptive Streaming. ; 2.2 MPEG-DASH and OMAF -- 2.3 MCTS Coding Scheme -- 3 Methodology -- 3.1 Tile-Based Panoramic Video Encoding -- 3.2 Multiple High Quality Streams -- 4 Experimental Results and Discussion -- 4.1 Experiment Setup -- 4.2 Analysis of the Results -- 5 Conclusion -- References -- Large Kernel Convolutional Attention Based U-Net Network for Inpainting Oracle Bone Inscription -- 1 Introduction -- 2 Method -- 2.1 Overview -- 2.2 Large Kernel Attention Block -- 2.3 U-Net Inpainting Generative Network -- 2.4 Global and Local Discriminative Networks -- 2.5 Loss Functions -- 3 Experimentation -- 3.1 Experimental Datasets and Settings -- 3.2 Evaluation Metrics -- 3.3 Experimental Results and Quantitative Evaluations -- 3.4 Ablation Study -- 4 Conclusion -- References -- L2DM: A Diffusion Model for Low-Light Image Enhancement -- 1 Introduction -- 2 Related Work -- 3 Proposed Method -- 3.1 Preliminaries -- 3.2 Autoencoder Module -- 3.3 ViTCondNet -- 3.4 Main Architecture -- 4 Experiments -- 4.1 Setup -- 4.2 Comparsion with SOTA Methods -- 4.3 Ablation Studies -- 5 Conclusion -- References -- Multi-domain Information Fusion for Key-Points Guided GAN Inversion -- 1 Introduction -- 2 Related Works -- 2.1 GAN Inversion -- 2.2 Latent Space Manipulation -- 3 Methodology -- 3.1 Overall Architecture -- 3.2 Unified Mapping Module -- 3.3 Multi Domain Information Fusion -- 3.4 Key-Point Patch Loss -- 3.5 Training Approaches for Inversion -- 4 Experiments -- 4.1 Implementation Details -- 4.2 Comparison with Inversion Method -- 4.3 Ablation Study and Analyse -- 5 Conclusion -- References -- Adaptive Low-Light Image Enhancement Optimization Framework with Algorithm Unrolling -- 1 Introduction -- 2 LIE Optimization Framework with Algorithm Unrolling -- 2.1 Unrolling LIE-QE Module -- 2.2 Loss of the LIE Optimization Framework -- 3 Experiment. ; 3.1 Evaluation of the Proposed Framework -- 3.2 Evaluation of Unrolling Decomposition Module -- 3.3 Comparison with Related Methods -- 4 Conclusion -- References -- Feature Matching in the Changed Environments for Visual Localization -- 1 Introduction -- 2 Related Work -- 2.1 Room Layout Estimation -- 2.2 Local Feature Matching -- 2.3 Datasets for Matching -- 3 Image Matching Dataset for Changed Indoor Environments -- 3.1 Design of the Dataset -- 3.2 Detailed Specifications -- 3.3 Obtaining Ground Truth Camera Pose -- 4 Method -- 4.1 Network Architecture -- 4.2 Loss Function -- 5 Experiment -- 5.1 Metrics and Datasets -- 5.2 Results -- 5.3 Implementation Details -- 6 Conclusion -- References -- To Be Critical: Self-calibrated Weakly Supervised Learning for Salient Object Detection -- 1 Introduction -- 2 Related Work -- 2.1 Salient Object Detection -- 2.2 Weakly Supervised Salient Object Detection -- 3 The Proposed Method -- 3.1 From Image-Level to Pixel-Level -- 3.2 Self-calibrated Training Strategy -- 3.3 Saliency Network -- 4 Dataset Construction -- 5 Experiments -- 5.1 Implementation Details -- 5.2 Datasets and Evaluation Metrics -- 5.3 Comparison with State-of-the-Arts -- 5.4 Ablation Studies -- 6 Conclusion -- References -- Image Visual Complexity Evaluation Based on Deep Ordinal Regression -- 1 Introduction -- 2 Related Work -- 2.1 Image Complexity Evaluation -- 2.2 Ordinal Regression -- 3 The Proposed Method -- 3.1 Improved the ICNet Model -- 3.2 Ordinal Regression Model -- 3.3 Total Loss Function -- 4 Experiment and Results -- 4.1 Dataset -- 4.2 Experimental Setup -- 4.3 Experimental Results Analysis -- 5 Conclusions -- References -- Low-Light Image Enhancement Based on Mutual Guidance Between Enhancing Strength and Image Appearance -- 1 Introduction -- 2 Related Works -- 3 Method -- 3.1 The Overall Framework of Our Model. ; 3.2 Mutual Guidance Module -- 3.3 Estimation of the Edge-Aware Lightness Map -- 4 Experiments -- 4.1 Experimental Settings -- 4.2 Experimental Results -- 4.3 Analysis of Our Method -- 5 Conclusion -- References -- Semantic-Guided Completion Network for Video Inpainting in Complex Urban Scene -- 1 Introduction -- 2 Related Work -- 3 Methods -- 3.1 Problem Formulation -- 3.2 Semantic Video Completion Network -- 3.3 Video Synthesis Network -- 3.4 Loss Functions -- 4 Experiments -- 4.1 Benchmarks and Evaluation Metrics -- 4.2 Results and Discussion -- 4.3 Ablation Experiments -- 5 Conclusion -- References -- Anime Sketch Coloring Based on Self-attention Gate and Progressive PatchGAN -- 1 Introduction -- 2 Related Work -- 2.1 Style Transfer -- 2.2 Automatic Sketch Coloring -- 2.3 User-Guided Coloring -- 2.4 Reference-Based Sketch Image Coloring -- 3 Methodology -- 3.1 Overall Workflow -- 3.2 Self-attention Gate -- 3.3 Progressive PatchGAN -- 3.4 Loss Function -- 4 Experimental Results and Analysis -- 4.1 Implementation Details -- 4.2 Qualitative Evaluation -- 4.3 Quantitative Evaluation -- 4.4 Ablation Study -- 5 Conclusions -- References -- TransDDPM: Transformer-Based Denoising Diffusion Probabilistic Model for Image Restoration -- 1 Introduction -- 2 Related Work -- 2.1 Image Restoration -- 2.2 Denoising Diffusion Probabilistic Models -- 2.3 Diffusion Models for Image Restoration -- 3 Transformer-Based Denoising Diffusion Restoration Models -- 3.1 Overall Pipeline -- 3.2 Multi-Head Cross-Covariance Attention (MXCA) -- 3.3 Gated Feed-Forward Network (GFFN) -- 3.4 Accelerated with Implicit Sampling -- 4 Experiment -- 4.1 Datasets and Evaluation Metrics -- 4.2 Implementation Details -- 4.3 Image Deraining Experiments -- 4.4 Image Dehazing Experiments -- 4.5 Motion Deblurring Experiments -- 4.6 Ablation Experiment -- 4.7 Limitations -- 5 Conclusion. ; References.
• Sommario/riassunto: The 13-volume set LNCS 14425-14437 constitutes the refereed proceedings of the 6th Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2023, held in Xiamen, China, during October 13–15, 2023. The 532 full papers presented in these volumes were selected from 1420 submissions. The papers have been organized in the following topical sections: Action Recognition, Multi-Modal Information Processing, 3D Vision and Reconstruction, Character Recognition, Fundamental Theory of Computer Vision, Machine Learning, Vision Problems in Robotics, Autonomous Driving, Pattern Classification and Cluster Analysis, Performance Evaluation and Benchmarks, Remote Sensing Image Interpretation, Biometric Recognition, Face Recognition and Pose Recognition, Structural Pattern Recognition, Computational Photography, Sensing and Display Technology, Video Analysis and Understanding, Vision Applications and Systems, Document Analysis and Recognition, Feature Extraction and Feature Selection, Multimedia Analysis and Reasoning, Optimization and Learning methods, Neural Network and Deep Learning, Low-Level Vision and Image Processing, Object Detection, Tracking and Identification, Medical Image Processing and Analysis. .
• Titolo autorizzato: Pattern recognition and computer vision
• ISBN: 981-9985-52-8
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910799216703321
• Lo trovi qui: Univ. Federico II
• Serie: Lecture Notes in Computer Science, . 1611-3349 ; ; 14435