【论文目录】人体表面细节重建相关论文(自用)
主要以单目RGB重建为主，包含部分相关的姿态估计方法。
目录
- 2020年
- Combining implicit function learning and parametric models for 3d human reconstruction
- PeelNet: Textured 3D reconstruction of human body using single view RGB image
- Do As I Do: Transferring Human Motion and Appearance between Monocular Videos with Spatial and Temporal Constraints
- PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization.
- Implicit functions in feature space for 3d shape reconstruction and completion
- Robust 3D Self-portraits in Seconds
- ARCH: Animatable Reconstruction of Clothed Humans
- （相关论文）
- 2019年
- PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization
- Learning to reconstruct people in clothing from a single RGB camera
- Siclope: Silhouette-based clothed people
- Livecap: Real-time human performance capture from monocular video
- Multi-Garment Net: Learning to Dress 3D People from Images
- Learning Dense Wide Baseline Stereo Matching for People
- 360-Degree Textures of People in Clothing from a Single Image
- Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Images
- 3DPeople: Modeling the Geometry of Dressed Humans
- Tex2Shape: Detailed Full Human Body Geometry from a Single Image
- Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild
- DeepHuman: 3D Human Reconstruction from a Single Image
- A Neural Network for Detailed Human Depth Estimation from a Single Image
- Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformation
- Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis
- （相关论文）
- *TexturePose: Supervising Human Mesh Estimation with Texture Consistency*
- *Self-Supervised Learning of 3D Human Pose using Multi-view Geometry*
- *Shape-Aware Human Pose and Shape Reconstruction Using Multi-View Images*
- *Temporally Coherent Full 3D Mesh Human Pose Recovery from Monocular Video*
- *VIBE: Video Inference for Human Body Pose and Shape Estimation*
- 2018年
- Detailed human avatars from monocular video
- Video based reconstruction of 3d people models
- Monoperfcap: Human performance capture from monocular video
- Deep volumetric video from very sparse multi-view performance capture
- Volumetric performance capture from minimal camera viewpoints
- Shape Reconstruction Using Volume Sweeping and Learned Photoconsistency
- Bodynet: Volumetric inference of 3d human body shapes
- （相关论文）
- ~2017年
2020年
Combining implicit function learning and parametric models for 3d human reconstruction
PeelNet: Textured 3D reconstruction of human body using single view RGB image
Do As I Do: Transferring Human Motion and Appearance between Monocular Videos with Spatial and Temporal Constraints
PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization.
Implicit functions in feature space for 3d shape reconstruction and completion
Robust 3D Self-portraits in Seconds
ARCH: Animatable Reconstruction of Clothed Humans
（相关论文）
High Accuracy Face Geometry Capture using a Smartphone Video
2019年
PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization
Learning to reconstruct people in clothing from a single RGB camera
Siclope: Silhouette-based clothed people
Livecap: Real-time human performance capture from monocular video
Multi-Garment Net: Learning to Dress 3D People from Images
Learning Dense Wide Baseline Stereo Matching for People
360-Degree Textures of People in Clothing from a Single Image
Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Images
3DPeople: Modeling the Geometry of Dressed Humans
Tex2Shape: Detailed Full Human Body Geometry from a Single Image
Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild
DeepHuman: 3D Human Reconstruction from a Single Image
A Neural Network for Detailed Human Depth Estimation from a Single Image
Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformation
Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis
（相关论文）
TexturePose: Supervising Human Mesh Estimation with Texture Consistency
Self-Supervised Learning of 3D Human Pose using Multi-view Geometry
Shape-Aware Human Pose and Shape Reconstruction Using Multi-View Images
Temporally Coherent Full 3D Mesh Human Pose Recovery from Monocular Video
VIBE: Video Inference for Human Body Pose and Shape Estimation
2018年
Detailed human avatars from monocular video
Video based reconstruction of 3d people models
