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

ISBN-13: 9789819984312 / Angielski

Qingshan Liu; Hanzi Wang; Zhanyu Ma

Spis treści

Deep Stereo Matching with Superpixel-based Feature and Cost Aggregation.- GMA3D: Local-Global Attention Learning to Estimate Occluded Motions of Scene Flow.- Diffusion-based 3D Object Detection with Random Boxes.- Blendshape-based Migratable Speech-driven 3D Facial Animation with Overlapping Chunking-Transformer.- FIRE: Fine Implicit Reconstruction Enhancement with Detailed Body Part Labels and Geometric Features.- Sem-Avatar: Semantic Controlled Neural Field for High-Fidelity Audio Driven Avatar.- Depth optimization for accurate 3D Reconstruction from light field images.- TriAxial Low-Rank Transformer for Efficient Medical Image Segmentation.- SACFormer: Unify Depth Estimation and Completion with Prompt.- Rotation-Invariant Completion Network.- Towards Balanced RGB-TSDF Fusion for Consistent Semantic Scene Completion by 3D RGB Feature Completion and a Classwise Entropy Loss Function.- FPTNet: Full Point Transformer Network for Point Cloud Completion.- Efficient Point-based Single Scale 3D Obiect Detection from Traffic Scenes.- Matching-to-Detecting: Establishing Dense and Reliable Correspondences between Images.- Solving Generalized Pose Problem of Central and Non-central Cameras.- RICH: Robust Implicit Clothed Humans Reconstruction from Multi-Scale Spatial Cues.-  An Efficient and Consistent Solution to the PnP Problem.- Autoencoder and Masked Image Encoding-based Attentional Pose Network.- A Voxel-Based Multiview Point Cloud Refinement Method via Factor Graph Optimization.-  SwinFusion: channel query-response based feature fusion for monocular depth estimation.-  PCRT: Multi-branch Point Cloud Reconstruction from a Single Image with Transformers.-  Progressive Point Cloud Generating by Shape Decomposing and Upsampling.- Three-dimensional Plant Reconstruction with Enhanced Cascade-MVSNet.-  Learning Key Features Transformer Network for Point Cloud Processing.-  Unsupervised Domain Adaptation for 3D Object Detection via Self-Training.- Generalizable Neural Radiance Field with Hierarchical Geometry Constraint.-  ACFNeRF: Accelerating and Cache-Free Neural Rendering via Point Cloud-based Distance Fields.- OctPCGC-Net: Learning Octree-Structured Context Entropy Model for Point Cloud Geometry Compression.- Multi-modal Feature Guided Detailed 3D Face Reconstruction from a Single Image.- Advanced License Plate Detector in Low-Quality Images with Smooth Regression Constraint.- A Feature Refinement Patch Embedding-Based Recognition Method for Printed Tibetan Cursive Script.- End-to-End Optical Music Recognition with Attention Mechanism and Memory Units Optimization.- Tripartite Architecture License Plate Recognition based on Transformer.- Focus the Overlapping Problem on Few-Shot Object Detection via Multiple Predictions.- Target-aware Bi-Transformer for Few-Shot Segmentation.- Convex Hull Collaborative Representation Learning on Grassmann Manifold with L_1 norm Regularization.- FUFusion: Fuzzy Sets Theory for Infrared and Visible Image Fusion.-Progressive Frequency-aware Network for Laparoscopic Image Desmoking.-A pixel-level segmentation method for water surface reflection detection