3D Human Reconstruction
49 papers with code • 8 benchmarks • 13 datasets
Benchmarks
These leaderboards are used to track progress in 3D Human Reconstruction
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
AGORA
BEHAVE
Dynamic FAUST
SSP-3D
MoVi
CAPE
HBW
X-Humans
Most implemented papers
PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization
facebookresearch/pifuhd
•
•
CVPR 2020
Although current approaches have demonstrated the potential in real world settings, they still fail to produce reconstructions with the level of detail often present in the input images.
3D Human Mesh Regression with Dense Correspondence
zengwang430521/DecoMR
•
•
CVPR 2020
This paper proposes a model-free 3D human mesh estimation framework, named DecoMR, which explicitly establishes the dense correspondence between the mesh and the local image features in the UV space (i. e. a 2D space used for texture mapping of 3D mesh).
Nerfies: Deformable Neural Radiance Fields
We present the first method capable of photorealistically reconstructing deformable scenes using photos/videos captured casually from mobile phones.
PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop
HongwenZhang/PyMAF
•
•
ICCV 2021
Regression-based methods have recently shown promising results in reconstructing human meshes from monocular images.
ICON: Implicit Clothed humans Obtained from Normals
First, ICON infers detailed clothed-human normals (front/back) conditioned on the SMPL(-X) normals.
SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos
With a simple yet effective motion-aware fully-connected network, SmoothNet improves the temporal smoothness of existing pose estimators significantly and enhances the estimation accuracy of those challenging frames as a side-effect.
AnthroNet: Conditional Generation of Humans via Anthropometrics
We present a novel human body model formulated by an extensive set of anthropocentric measurements, which is capable of generating a wide range of human body shapes and poses.
Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer
As a result, our CONTHO achieves state-of-the-art performance in both human-object contact estimation and joint reconstruction of 3D human and object.
Self-supervised Learning of Motion Capture
chingswy/HumanPoseMemo
•
•
NeurIPS 2017
In this work, we propose a learning based motion capture model for single camera input.
DeepHuman: 3D Human Reconstruction from a Single Image
ZhengZerong/DeepHuman
•
•
ICCV 2019
We propose DeepHuman, an image-guided volume-to-volume translation CNN for 3D human reconstruction from a single RGB image.
