Chapter 1 Introduction 1.1 3D Object Modeling 1.1.1 Single-View 3D Reconstruction 1.1.2 Multi-View 3D Reconstruction Method 1.2 3D Face Modeling 1.2.1 3D Face Keypoint Detection 1.2.2 3D Face Reconstruction 1.3 3D Human Body Modeling 1.3.1 3D Human Pose Estimation 1.3.2 3D Human Body Reconstruction 1.4 3D Reconstruction Modeling 1.5 Outline of the Work Bibliography Chapter 2 3D Object Modeling 2.1 Single-View 3D Object Modeling 2.1.1 Multi-Scale Edge-Guided Learning for 3D Reconstruction 2.1.2 Multi-Granularity Relationship Reasoning Network for High-Fidelity 3D Shape Reconstruction 2.1.3 3D Shape Reconstruction Based on Dynamic Multi-Branch Information Fusion 2.1.4 Hierarchical Feature Learning Network for 3D Object Reconstruction 2.2 Multi-View 3D Object Modeling 2.2.1 High-Resolution Multi-View Stereo with Dynamic Depth Edge Flow 2.2.2 Global Contextual Complementary Network for Multi-View Stereo 2.2.3 Attention-Guided Multi-View Stereo Network for Depth Estimation 2.2.4 Self-Supervised Edge Structure Learning for Multi-View Stereo and Parallel Optimization 2.2.5 Layered Decoupled Complementary Networks for Multi-View Stereo 2.2.6 Global Balanced Networks for Multi-View Stereo Bibliography Chapter 3 3D Face Keypoint Detection 3.1 Learning Relation-Sensitive Structured Network for Robust Face Alignment 3.1.1 Introduction 3.1.2 Proposed Method 3.1.3 Experiments 3.1.4 Conclusion 3.2 Multi-Agent Deep Collaboration Learning for Face Alignment under Different Perspectives 3.2.1 Introduction 3.2.2 Proposed Method 3.2.3 Experiments 3.2.4 Conclusion 3.3 Towards Accurate 3D Face Alignment under Extreme Scenarios via Multi-Granularity Perturbation Relearning 3.3.1 Introduction 3.3.2 Proposed Method 3.3.3 Loss Function 3.3.4 Experiments 3.3.5 Conclusion Bibliography Chapter 4 3D Face Reconstruction 4.1 Towards Rich-Detail 3D Face Reconstruction and Dense Alignment via Multi-Scale Detail Augmentation 4.1.1 Introduction 4.1.2 Proposed Method 4.1.3 Experiments
4.1.4 Conclusion 4.2 Multi-Attribute Regression Network for Face Reconstruction 4.2.1 Introduction 4.2.2 Proposed Method 4.2.3 Experiments 4.2.4 Conclusion 4.3 Geometry Normal Consistency Loss for 3D Face Reconstruction and Dense Alignment 4.3.1 Introduction 4.3.2 Proposed Method 4.3.3 Experiments 4.3.4 Conclusion 4.4 Complementary Learning Network for 3D Face Reconstruction and Alignment 4.4.1 Introduction 4.4.2 Proposed Method 4.4.3 Experiments 4.4.4 Conclusion 4.5 Graph Structure Reasoning Network for Face Alignment and Reconstruction 4.5.1 Introduction 4.5.2 Proposed Method 4.5.3 Experiments 4.5.4 Conclusion 4.6 Unsupervised Shape Enhancement and Factorization Machine Network for 3D Face Reconstruction 4.6.1 Introduction 4.6.2 Proposed Method 4.6.3 Experiments 4.6.4 Conclusion 4.7 A Detail Geometry Learning Network for High-Fidelity Face Reconstruction 4.7.1 Introduction 4.7.2 Proposed Method 4.7.3 Experiments 4.7.4 Conclusion 4.8 A Bi-Directional Optimization Network for De-Obscured 3D High-Fidelity Face Reconstruction 4.8.1 Introduction 4.8.2 Proposed Method 4.8.3 Experiments 4.8.4 Conclusion Bibliography Chapter 5 3D Human Pose Estimation 5.1 Multi-Hybrid Extractor Network for 3D Human Pose Estimation 5.1.1 Introduction 5.1.2 Proposed Method 5.1.3 Experiments 5.1.4 Conclusion 5.2 3D Human Pose Estimation Based on Center of Gravity 5.2.1 Introduction 5.2.2 Proposed Method 5.2.3 Experiments 5.2.4 Conclusion 5.3 Edge-Angle Structure Constraint Loss for 3D Human Pose Estimation 5.3.1 Introduction
5.3.2 Related Works 5.3.3 Proposed Method 5.3.4 Experiments 5.3.5 Conclusion Bibliography Chapter 6 3D Human Body Reconstruction 6.1 Two-Stage Co-Segmentation Network Based on Discriminative Representation for Recovering Human Mesh from Videos 6.1.1 Introduction 6.1.2 Related Works 6.1.3 Proposed Method 6.1.4 Experiments 6.1.5 Conclusion 6.2 Frame-Level Feature Tokenization Learning for Human Body Pose and Shape Estimation 6.2.1 Introduction 6.2.2 Related Works 6.2.3 Proposed Method 6.2.4 Experiments 6.2.5 Conclusion 6.3 Time-Frequency Awareness Network for Human Mesh Recovery from Videos 6.3.1 Introduction and Related Works 6.3.2 Proposed Method 6.3.3 Experiments 6.3.4 Conclusion 6.4 Spatio-Temporal Tendency Reasoning for Human Body Pose and Shape Estimation from Videos 6.4.1 Introduction and Related Works 6.4.2 Proposed Method 6.4.3 Experiments 6.4.4 Conclusion Bibliography Chapter 7 3D Reconstruction Modeling 7.1 Replay Attention and Data Augmentation Network for 3D Face and Object Reconstruction 7.1.1 Introduction 7.1.2 Related Works 7.1.3 Proposed Method 7.1.4 Experiments 7.1.5 Conclusion 7.2 A Lightweight Grouped Low-Rank Tensor Approximation Network for 3D Mesh Reconstruction from Videos 7.2.1 Introduction 7.2.2 Proposed Method 7.2.3 Experiments 7.2.4 Conclusion Bibliography
[