Image and Graphics Technologies and Applications

This book constitutes the refereed proceedings of the 19th Chinese Conference on Image and Graphics Technologies and Applications, IGTA 2024, held in Beijing, China, during August 1618, 2024.

The 36 full papers included in this book were carefully reviewed and selected from 91 submissions. The papers focus on image processing, computer graphics, and related topics, including but not limited to image analysis and understanding, computer vision and pattern recognition, data mining, virtual reality and augmented reality, and image technology applications.

Inhalt

.- Remote Sensing Scene Classification Method Based on Multi-Scale Local Attention Network.
.- An Iterative Method for Single Image Stripe Nonuniformity Correction.
.- Optimized Recognition and Depth Estimation for Fruit Picking Robots.
.- BM3D-UGanNet: A Hybrid Deep Learning Network for Low-Light Thangka Image Enhancement.
.- Stagewise Positional Encoding for Implicit Neural Representation of Image.
.- Image Enhancement Based on a Diffusion Model Guided by No-Reference Image Quality Assessment.
.- Adaptive Pixel Pair Generation Strategy for Image Matting Methods based on Pixel Pair Optimization.
.- EdgCNN:Thangka line drawing extraction based on CNN.
.- Fire detection based on flame enhancement for weak fires.
.- HDR-TDC: High Dynamic Range Imaging with Transformer Deformable Convolution.
.- Enhancing Fine-Tuning Performance of Text-to-Image Diffusion Models for Few-Shot Image Generation Through Contrastive Learning.
.- Generalized diffusion models for non-Gaussian noise.
.- Phase Error Correction Algorithm Based on Complementary Gray Code and Reverse Error Compensation.
.- Defect Detection based on Normalized Attention Mechanism and Multi-level Feature Fusion.
.- Study on different apple ripeness detection based on improved YOLOv5.
.- Learning Features by Minimizing the Interframe Differences.
.- VTR-former: Vision Token Rolling Transformer for Weakly Supervised Temporal Text Localization.
.- CMME-YOLO: Composite Microscale Multi-Stream Enhanced Model for PCB Defect Detection.
.- Multi-behavior Recommendation with Hypergraph Contrastive Learning.
.- Contrastive Learning-Based Dual Path Fusion Network for Group Activity Recognition.
.- Microclimate Regulation in Glass Greenhouses: Simulation of Wind Velocity and Temperature Fields and Design Model of the Greenhouse Fans.
.- Visualization of Spatial and Temporal Information of Railway Heritage in Modern China.
.- Exploration of New Energy Electric Vehicle Development Based on SSA-SVR Model.
.- Long Sequences Generation for Motion Diffusion Models.
.- Gaussian Replacement: Gaussians-Mesh Joint Rendering for Real-time VR Interaction.
.- Multi-View Intention Recognition in Face-to-Face Communication.
.- HSINet: A Hybrid Semantic Integration Network for Medical Image Segmentation.
.- VT Prompt Tuning: Improving Portrait Generation With Combined Visual Prompt and Text Prompt in Stable Diffusion Model.
.- Semantic segmentation of remote sensing images based on U-Net.
.- MRFFA-Net: A Multi-scale Residual Feature Fusion and Attention Mechanisms for Retinal Vessel Segmentation.
.- Optical flow generation method based on multi-scale feature enhancement of compressed video bitstream information.