3D Multi-Person Mesh Recovery
10 papers with code • 2 benchmarks • 2 datasets
AGORA
Relative Human
Most implemented papers
Monocular, One-stage, Regression of Multiple 3D People
Through a body-center-guided sampling process, the body mesh parameters of all people in the image are easily extracted from the Mesh Parameter map.
Expressive Body Capture: 3D Hands, Face, and Body from a Single Image
vchoutas/smplify-x
•
•
CVPR 2019
We use the new method, SMPLify-X, to fit SMPL-X to both controlled images and images in the wild.
Monocular Expressive Body Regression through Body-Driven Attention
To understand how people look, interact, or perform tasks, we need to quickly and accurately capture their 3D body, face, and hands together from an RGB image.
AGORA: Avatars in Geography Optimized for Regression Analysis
pixelite1201/agora_evaluation
•
•
CVPR 2021
Additionally, we fine-tune methods on AGORA and show improved performance on both AGORA and 3DPW, confirming the realism of the dataset.
Collaborative Regression of Expressive Bodies using Moderation
YadiraF/PIXIE
•
•
Second, human shape is highly correlated with gender, but existing work ignores this.
Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Images
nicolasugrinovic/size_depth_disambiguation
•
•
We address the problem of multi-person 3D body pose and shape estimation from a single image.
One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer
IDEA-Research/OSX
•
•
CVPR 2023
It is challenging to perform this task with a single network due to resolution issues, i. e., the face and hands are usually located in extremely small regions.
Reconstructing Groups of People with Hypergraph Relational Reasoning
boycehbz/GroupRec
•
•
ICCV 2023
To address the obstacles, we fully exploit crowd features for reconstructing groups of people from a monocular image.
SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation
caizhongang/SMPLer-X
•
•
NeurIPS 2023
1) For the data scaling, we perform a systematic investigation on 32 EHPS datasets, including a wide range of scenarios that a model trained on any single dataset cannot handle.
Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot
naver/multi-hmr
•
•
We present Multi-HMR, a strong single-shot model for multi-person 3D human mesh recovery from a single RGB image.
