Image and Graphics: 11th International Conference, Icig 2021, Haikou, China, August 6-8, 2021, Proceedings, Part III

ISBN-13: 9783030873608 / Angielski / Miękka / 2021 / 848 str.

Peng, Yuxin

Opis

This three-volume set LNCS 12888, 12898, and 12890 constitutes the refereed conference proceedings of the 11^th International Conference on Image and Graphics, ICIG 2021, held in Haikou, China, in August 2021.* The 198 full papers presented were selected from 421 submissions and focus on advances of theory, techniques and algorithms as well as innovative technologies of image, video and graphics processing and fostering innovation, entrepreneurship, and networking.*The conference was postponed due to the COVID-19 pandemic.

Spis treści

3D Computer Vision.- Efficient Depth-Included Residual Refinement Network for RGB-D Saliency Detection.- Learning Cross-domain Descriptors for 2D-3D Matching with Hard Triplet Loss and Spatial Transformer Network.- A Stereo Matching Method for Three-dimensional Eye Localization of Autostereoscopic Display.- Scaling Invariant Harmonic Wave Kernel Signature for 3D Point Cloud Similarity.- PST-NET: Point Cloud Sampling via Point-based Transformer.- Bird Keypoint Detection via Exploiting 2D Texture and 3D Geometric Features.- Rotation Aware 3D Point Cloud Vehicle Detection.- Improved 3D Morphable Model for Facial Action Unit Synthesis.- Semantic Guided Multi-directional Mixed-color 3D Printing.- KeypointNet: Ranking Point Cloud for Convolution Neural Network.- Geometric Context Sensitive Loss and its Application for Nonrigid Structure from Motion.- 3D Reconstruction from Single-view Image Using Feature Selection.- Computational Photography.- Adaptive Steganography Based on Image Edge Enhancement and Automatic Distortion Learning.- No-Reference Image Quality Assessment via Broad Learning System.- Hindsight Curriculum Generation Based Multi-Goal Experience Replay.- Gesture-Based Autonomous Diving Buddy for Underwater Photography.- Adaptive Underwater Image Enhancement via Color Channel Compensation Based on Optical Restoration and Fusion.- A Fast Domain Adaptation Network for Image Super-Resolution.- Using Conv-LSTM to Refine Features for Lightweight Image Super-Resolution Network.- No-Reference Image Quality Assessment for Contrast Distorted Images.- Multi-Scale Deformable Deblurring Kernel Prediction for Dynamic Scene Deblurring.- Structure Adaptive Filtering for Edge-preserving Image Smoothing.- Robust Image Cropping by Filtering Composition Irrelevant Factors.-Robust Chinese License Plate Generation via Foreground Text and Background Separation.- Towards Boosting Channel Attention for Real Image Denoising: Sub-band Pyramid Attention.- Tiny Person Pose Estimation via Image and Feature Super Resolution.- Improved VIBE Shadow Elimination Method with Adaptive Threshold in the Environment of Tarmac Monitoring.- Technological Development of Image Aesthetics Assessment.- Noise Robust Video Super-resolution without Training on Noisy Data.- Shadow Detection and Removal based on Multi-Task Generative Adversarial Networks.- A Multi-Path Neural Network for Hyperspectral Image Super-Resolution.- Nighttime Thermal Infrared Image Colorization with Dynamic Label Mining.- SA-GNN: Stereo Attention and Graph Neural Network for Stereo Image Super-Resolution.- Ground-to-Aerial Image Geo-Localization With Cross-View Image Synthesis.- Self-supervised Hyperspectral and Multispectral Image Fusion in Deep Neural Network.-Degradation Reconstruction Loss: A Perceptual-Oriented Super-Resolution Framework for Multi-Downsampling Degradations.- Auto-calibration of exit pupils for autostereoscopic display with the eye tracker.- Computer Graphics and Visualization.- Semantic and Optical Flow Guided Self-supervised Monocular Depth and Ego-motion Estimation.- Frequency Transfer Model: Generating High Frequency Components for Fluid Simulation Details Reconstruction.- Low Crosstalk Multi-view 3D Display Based on Parallax Barrier with Dimmed Subpixel.- DRLFNet: A Dense-connection Residual Learning Neural Network for Light Field Super Resolution.- PSF estimation of simple lens based on circular partition strategy.- Photometric Stereo Based on Multiple Kernel Learning.- Hair Salon: A Geometric Example-based Method to Generate 3D Hair Data.- Single scene image editing based on deep intrinsic decomposition.- 3A2A: A Character Animation Pipeline for 3D-Assisted 2D-Animation.- Motion and Tracking.- A Detection and Tracking Combined Network for Long-term Tracking.- Scale Adaptive Target Tracking Based On Kernel Correlation Filter and Residual Network.- Adaptive Gaussian-like response Correlation Filter in UAV Tracking.- Online Scene Text Tracking with Spatial-Temporal Relation.- Equivalence of Correlation Filter and Convolution Filter in Visual Tracking.- LSNT: A Lightweight Siamese Network based Tracker.- A Virtual Mouse Based on Parallel Cooperation of Eye Tracker and Motor Imagery.- A Monocular Reflection-free Head-mounted 3D Eye Tracking System.- Video analysis and understanding.- Coding and quality evaluation of affordable 6DoF video content.- Adaptive Self-Supervised Depth Estimation in Monocular Videos.- Drowning Detection Based on Video Anomaly Detection.- NBA Basketball Video Summarization for News Report via Hierarchical-grained Deep Reinforcement Learning.- Efficient Unsupervised Monocular Depth Estimation with Inter-Frame Depth Interpolation.- Video Playback Quality Evaluation Based on User Expectation and Memory.- Talking Face Video Generation With Expression.- Protecting Encrypted Video Stream Against Information Leak using Adversarial Traces.- Adaptive Spatio-Temporal Convolutional Network for Video Deblurring.- TS-UNet: A Temporal Smoothed UNet for Video Anomaly Detection.- DBAM: Dense Boundary and Actionness Map for Action Localization in Videos via Sentence Query.- A deep transfer learning-based object tracking algorithm for hyperspectral video.