HierarchicalProbabilistic3DHuman
SPIN
HierarchicalProbabilistic3DHuman | SPIN | |
---|---|---|
5 | 1 | |
186 | 783 | |
- | - | |
3.5 | 3.9 | |
3 months ago | 5 months ago | |
Python | Python | |
MIT License | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
HierarchicalProbabilistic3DHuman
-
[R] Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild
Github
Code for https://arxiv.org/abs/2110.00990 found: https://github.com/akashsengupta1997/HierarchicalProbabilistic3DHuman
-
Nvidia tool generates full 3D models from a single still image
I don't know of one yet. Lot of people are working on it, using various strategies. The grail being able to provide a virtual fitting-room experience. Or monitoring fitness of individuals.
A 2021 paper with code (I haven't tried it): https://github.com/akashsengupta1997/hierarchicalprobabilist... to generate a 3d morph-able human-shape in the correct pose from a single picture.
A picture always has scale uncertainty (a 2-meter human viewed from 1 meter away look the same that a 1-meter human viewed from 0.5 meter away), so that is an additional problem that must be taken care of.
But now recent phone have 3d sensor that provide information that could be useful.
To generate 3d human models there is also makehuman . In the old days there was a soft called facegen, that could generate 3d face models and could automatically fit their parameters to two pictures using an iterating refinement procedure.
Deep-learning usually estimate everything jointly in a single step so they are faster, but often less accurate. But there exist models that learn to refine a previously generated model, so you can apply them repeatedly and get improved quality (Denoising Diffusion Probabilistic Models is one generic class of models that does this).
-
3D reconstruction models for human body
Nevertheless, I find that reading a few related work sections of new papers gives me a good idea about the seminal papers in a field, since they will be repeatedly cited. Here is shameless self-plug to something I worked on: https://github.com/akashsengupta1997/HierarchicalProbabilistic3DHuman. I am not really a big name researcher and this paper probably won't be super impactful, so feel free to ignore the method, but I would recommend reading the related work section since it lists some of the impactful papers from good researchers. (Also check out related work sections from other papers to cross-reference).
SPIN
-
3D reconstruction models for human body
The other reply has listed some good references if related work sections are TL;DR, however I would add: SMPLify - https://files.is.tue.mpg.de/black/papers/BogoECCV2016.pdf HMR - https://github.com/akanazawa/hmr SPIN - https://github.com/nkolot/SPIN as very important works (albeit outdated).
What are some alternatives?
pifuhd - High-Resolution 3D Human Digitization from A Single Image.
hmr - Project page for End-to-end Recovery of Human Shape and Pose
hierarchicalprobabilist
VIBE - Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"
smplx - SMPL-X
videoavatars - This repository contains code corresponding to the paper Video based reconstruction of 3D people models.
SMPL - NumPy, TensorFlow and PyTorch implementation of human body SMPL model and infant body SMIL model.
Anatomy3D - Anatomy-aware 3D Human Pose Estimation in Videos