Pattern Recognition and Computer Vision: 6th Chinese Conference, Prcv 2023, Xiamen, China, October 13-15, 2023, Proceedings, Part XI

ISBN-13: 9789819985517 / Angielski

Qingshan Liu; Hanzi Wang; Zhanyu Ma

Spis treści

Efficiently Amalgamated CNN-Transformer Network for Image Super-Resolution Reconstruction.- A hybrid model for video compression based on the  fusion of feature compression framework and multi-object tracking network.- Robust Degradation Representation via Efficient Diffusion Model for Blind Super-resolution.- MemDNet:Memorizing more exogenous information to dehaze natural hazy image.- Technical Quality-Assisted Image Aesthetics Quality Assessment.- Self-Supervised Low-Light Image Enhancement via Histogram Equalization Prior.- Enhancing GAN Compression by Image Probability Distribution Distillation.- HDTR-Net: A Real-Time High-Definition Teeth Restoration Network for Arbitrary Talking Face Generation Methods.- Multi-stream-based Low-latency Viewport Switching Scheme for Panoramic Videos.- Large Kernel Convolutional Attention based U-Net Network for Inpainting Oracle Bone Inscription.- L^2DM: A Diffusion Model for Low-Light Image Enhancement.- Multi-domain Information Fusion for Key-points Guided GAN Inversion.- Adaptive Low-Light Image Enhancement Optimization Framework with Algorithm Unrolling.- Feature Matching in the Changed Environments for Visual Localization.- To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection.- Image Visual Complexity Evaluation Based on Deep Ordinal Regression.- Low-light Image Enhancement Based on Mutual Guidance between Enhancing Strength and Image Appearance.- Semantic-Guided Completion Network for Video Inpainting in Complex Urban Scene.- Anime Sketch Coloring Based on Self-Attention Gate and Progressive PatchGAN.- TransDDPM: Transformer-based Denoising Diffusion Probabilistic Model for image Restoration.- One-Stage Wireframe Parsing in Fish-eye Images.- Out-of-Distribution with Text-to-Image Diffusion Models.- Generalized Zero-Shot Learning with Noisy Labeled Data.- Q-TrHDRI: A Qurey-based Transformer for High Dynamic Range Imaging with Dynamic Scenes.- FRNet: Improving Face De-Occlusion via Feature Reconstruction.- Semantically Guided Bi-level Adaptation for Cross Domain Crowd Counting.- Joint Priors-Based Restoration Method for Degraded Images Under Medium Propagation.- GridIIS: Grid based Interactive Image Segmentation.- ADORE: Adaptive Diffusion Optimized Restoration for AI-generated Facial Imagery.- TU-former: A hybrid U-shaped Transformer network for SAR image denoising.- New Insights on the Generation of Rain Streaks: Generating-Removing United Unpaired Image Deraining Network.- Knowledge Transfer via Leveraging Teacher-Student Network with Visual Attention to Enhance Atmospheric Sand Image Restoration.- Enhancing Image-to-Image Translation with Contrast Loss Constrained Generators and Selective Neighborhood Sampling.- Dynamic Neural Networks for Adaptive Implicit Image Compression.- Misalignment Insensitive Perceptual Metric for Full Reference Image Quality Assessment.- A Mutual Enhancement Framework for Specular Highlight Detection and Removal.- Pixel-Level Sonar Image JND Based on Inexact Supervised Learning.- Discriminative Activation of Information is what you need in Image Super-Resolution Transformer.- SentiImgBank: A Large Scale Visual Repository for Image Sentiment Analysis.- MSED: A Robust Ellipse Detector With Multi-Scale Merging and Validation.