Advances in Computer Graphics: 38th Computer Graphics International Conference, CGI 2021, Virtual Event, September 6-10, 2021, Proceedings

Computer Animation.- Temporal Parameter-free Deep Skinning of Animated Meshes.- The impact of animations in the perception of a simulated crowd.- Computer Vision.- Virtual haptic system for shape recognition based on local curvatures.- Stable Depth Estimation within Consecutive Video Frames.- Progressive Multi-Scale Reconstruction for Guided Depth Map Super-Resolution via Deep Residual Gate Fusion Network.- SE_EDNet: A Robust Manipulated Faces Detection Algorithm.- PointCNN-based Individual Tree Detection Using LiDAR Point Clouds.- Variance weight distribution network based Noise Sample Learning for Robust Person Re-identification.- Monocular Dense SLAM with Consistent Deep Depth Prediction.- Sketch-based 3D Garment Generation with Shape-adapted.- Geometric Computing.- Light-Weight Multi-View Topology Consistent Facial Geometry and Reflectance Capture.- Real-Time Fluid Simulation with Atmospheric Pressure Using Weak Air Particles.- Human Poses and Gestures.- Reinforcement Learning for Quadruped Locomotion.- Partially Occluded Skeleton Action Recognition based on Multi-stream Fusion Graph Convolutional Networks.- Social-Scene-Aware Generative Adversarial Networks for Pedestrian Trajectory Prediction.- Image Processing.- Cecid Fly Defect Detection in Mangoes using Object Detection Frameworks.- Twin-Channel Gan: Repair Shape with Twin -Channel Generative Adversarial Network and Structural Constraints.- CoPaint: Guiding Sketch Painting with Consistent Color and Coherent Generative Adversarial Networks.- Multi-Stream Fusion Network for Multi-Distortion Image Super-Resolution.- Generative Face Parsing Map Guided 3D Face Reconstruction Under Occluded Scenes.- Compact Double Attention Module Embedded CNN for Palmprint Recognition.- M2M: Learning to Enhance Low-light Image from Model to Mobile FPGA.- Character Flow Detection and Rectification for Scene Text Spotting.- A Deep Learning Method for 2D Image Stippling.- Medical Imaging.- In Silico Heart Versatile Graphical Interface with Systole and Diastole Phases Customizable for Diversified Arrhythmias Simulations.- ADD-Net: Attention U-Net with Dilated Skip Connection and Dense Connected Decoder for Retinal Vessel Segmentation.- BDFNet: Boundary-assisted and Discriminative Feature Extraction Network for COVID-19 Lung Infection Segmentation.- A Classification Network for Ocular Diseases Based on Structure Feature and Visual Attention.- Physics-based Simulation.- DSNet: Dynamic skin deformation prediction by Recurrent Neural Network.- Curvature Analysis of Sculpted Hair Meshes for Hair Guides Generation.- Synthesizing Human Faces with Local Weight Autoencoder.- CFMNet: Coarse-to-Fine Cascaded Feature Mapping Network for Hair Attribute Transfer.- Rendering and Textures.- Dynamic Shadow Synthesis Using Silhouette Edge Optimization.- DDISH-GI: Dynamic Distributed Spherical Harmonics Global Illumination.- Simplicity Driven Edge Refinement and Color Reconstruction in Image Vectorization.- Temporal-Consistency-Aware Video Color Transfer.- An improved advancing-front-Delaunay method for triangular mesh generation.- Robotics and Vision.- The use of a social robot in elderly home for recreational activities.- Resilient Navigation among dynamic agents with hierarchical reinforcement learning.- Visual Analytics.- MeshChain: Secure 3D model and intellectual property management powered by blockchain technology.- Image emotion analysis based on the distance relation of emotion categories via deep metric learning.- How much do we perceive geometric features, personalities and emotions in avatars?.- High-Dimensional Dataset Simplification by Laplace-Beltrami Operator.- VR/AR.- Characterizing Visual Acuity in the use of Head Mounted Displays.- Effects of Different Proximity-based Feedback on Virtual Hand Pointing in Virtual Reality.- Virtual Scenes Construction Promotes Traditional Chinese Art Preservation.- A Prelimin