三维人体建模作为计算机人体仿真的一个组成部分，一直是人们研究的热点之一。自交互式计算机图形学诞生之日起，就有学者不断探索计算机人体建模技术。从线框建模、实体建模、曲面建模发展到基于物理的建模，已取得重大进展。3维度人体建模在医学图像、生物医学、手势识别、视频会议、视频游戏、自动新闻播放、电影制作、材料变形、图象压缩等方面都有实际应用价值。
本资源整理了最近几年基于深度学习技术的三维人体重构（建模）相关的最新论文、资源、代码和公开数据集，分享给需要的朋友。
资源整理自网络，源地址：https://github.com/chenweikai/Body_Reconstruction_References
目录
论文资源列表
Multi-view Reconstruction
1. Deep Learning
[ICCV19] Shape-Aware Human Pose and Shape Reconstruction Using Multi-View Images
[ICCV19] TexturePose: Supervising Human Mesh Estimation with Texture Consistency
[ICCV19] Human Mesh Recovery From Monocular Images via a Skeleton-Disentangled Representation
[ECCV18] Deep Volumetric Video From Very Sparse Multi-View Performance Capture
[ECCV18] Bodynet: Volumetric inference of 3d human body shapes
[ECCV18] Volumetric performance capture from minimal camera viewpoints
2. Shape from Silhouette
[CGF16] 3d body shapes estimation from dressed-human silhouettes
[ICCV15] Interactive visual hull refinement for specular and transparent object surface reconstruction
[HPG13] Real-time high-resolution sparse voxelization with application to image-based modeling
[TOG08] Articulated Mesh Animation from Multi-view Silhouettes [data]
[ECCV06] Carved visual hulls for image-based modeling
[3DPVT06] Visual shapes of silhouette sets
[CVIU04] Silhouette and stereo fusion for 3d object modeling
[CVPR03] Visual hull alignment and refinement across time: A 3d reconstruction algorithm combining shape-from-silhouette with stereo
[CGIT00] Image-based visual hulls
3. Multi-view Stereo
[UIST16] Holoportation: Virtual 3d teleportation in real-time
[SIGGRAPH15] High-quality streamable free-viewpoint video
[TVCG10] A point-cloud-based multiview stereo algorithm for free-viewpoint video
[SIGGRAPH08] Markerless garment capture
[CGA07] Surface capture for performance-based animation
[TVC05] Scalable 3d video of dynamic scenes
4. Photometric Stereo
[ICCV11] Shading-based dynamic shape refinement from multi-view video under general illumination
[SIGGRAPH_Asia09] Dynamic shape capture using multi-view photometric stereo
5. Template based Approaches
[TOG13] On-set performance capture of multiple actors with a stereo camera
[ECCV12] Full body performance capture under uncontrolled and varying illumination: A shading-based approach
[CVPR11] Markerless motion capture of interacting characters using multi-view image segmentation
[SIGGRAPH_Asia10] Video-based reconstruction of animatable human characters
[SIGGRAPH08] Performance capture from sparse multi-view video
[CVPR09] Motion capture using joint skeleton tracking and surface estimation
[CVPR08] Robust fusion of dynamic shape and normal capture for high-quality reconstruction of time-varying geometry
6. Parametric Models
[ICCV19] Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop
[CVPR19] Expressive Body Capture: 3D Hands, Face, and Body from a Single Image
[CVPR18 Oral] Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies
[CVPR18] End-to-end recovery of human shape and pose [code and data]
[CVPR17] Unite the people: Closing the loop between 3d and 2d human representations [project page(code and data)]
[BMVC17] Indirect deep structured learning for 3D human body shape and pose prediction
[ECCV16] Keep it SMPL: Automatic estimation of 3d human pose and shape from a single image[code]
[SIGGRAPH_Asia15] SMPL: A skinned multi-person linear model
[TOG14] Mosh: Motion and shape capture from sparse markers
[CVPR10] Multilinear pose and body shape estimation of dressed subjects from image sets
[ICCV09] Estimating Human Shape and Pose from a Single Image
[CVPR07] Detailed human shape and pose from images
[SIGGRAPH05] SCAPE: shape completion and animation of people
[CVIU01] Tracking and modeling people in video sequences
Single-view Reconstruction
[ICCV19] Tex2Shape: Detailed Full Human Body Geometry From a Single Image
[ICCV19] PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization
[ICCV19] Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Images
[ICCV19] 3DPeople: Modeling the Geometry of Dressed Humans
[ICCV19] DeepHuman: 3D Human Reconstruction From a Single Image
[ICCV19] A Neural Network for Detailed Human Depth Estimation From a Single Image
[ICCV19] Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild
[CVPR19 Oral] SiCloPe: Silhouette-Based Clothed People
[CVPR19 Oral] Convolutional Mesh Regression for Single-Image Human Shape Reconstruction
[CVPR19 Oral] Detailed Human Shape Estimation from a Single Image by Hierarchical mesh deformation
[CVPR19] Learning to Reconstruct People in Clothing from a Single RGB Camera
[CVPR19] SimulCap: Single-View Human Performance Capture with Cloth Simulation
[CVPR19] Photo Wake-Up: 3D Character Animation from a Single Photo
[TOG19] LiveCap: Real-time Human Performance Capture from Monocular Video
[CVPR18] End-to-end recovery of human shape and pose [code and data]
[3DV18] Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose
[ICCV09] Estimating Human Shape and Pose from a Single Image
4D-Scans
[SIGGRAPH17] ClothCap: seamless 4D clothing capture and retargeting
Datasets and Code
MPI datasets and code
BUFF
Dynamic FAUST
CVSSP3D
Mixamo
Human3.6M
3DPeople
THuman
RenderPeople
CLOTH3D(not released yet)
Multi-Garment Net
