Synthesizing Long-Term 3D Human Motion and Interaction in 3D in CVPR2021

Overview

Long-term-Motion-in-3D-Scenes

This is an implementation of the CVPR'21 paper "Synthesizing Long-Term 3D Human Motion and Interaction in 3D".

Please check our paper and the project webpage for more details.

Citation

If you use our code or paper, please consider citing:

@article{wang2020synthesizing,
  title={Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes},
  author={Wang, Jiashun and Xu, Huazhe and Xu, Jingwei and Liu, Sifei and Wang, Xiaolong},
  journal={arXiv preprint arXiv:2012.05522},
  year={2020}
}

Dependencies

Requirements:

Datasets

We use PROX and PROXE datasets as our training data. After downloading them, please put them in './data/'. We provide generate_routepose_data.ipynb and generate_sub_data.ipynb for data generation. Note in PROX, the human meshes and the scene meshes are not in the same area in the world coordinates. Different from PROX and PROXE, we apply the inverse of the camera extrinsics to the scene mesh. Since the scene is the input and we need it to be aligned with the human bodies. This is done in the data generation code. Thus for contact calculating, you do not need to apply transformation to them. While for collision calculating, you still need to apply the transformation to the human bodies similar to PROXE to make it be aligned with SDF. Please be careful with this during training or testing, especially if you want to test on other scenes such as Matterport3D. Please put body_segments data in './data/' as well.

Demo

We provide demo.ipynb to help you play with our method. Before running, please put a downsampled MPH16.ply mesh and the SDF data of this scene in './demo_data/'. You can download them from PROX and PROXE. Still, please be careful with the camera extrinsics when you want to test other scenes, make sure the human body is in the scene. This code will also show you how to optimize the whole motion.

Models

We use SMPL-X to represent human bodies. Please download the SMPL-X models and put them in './models/' and it may look like './models/smplx/SMPLX_NEUTRAL.npz'. Please download vposer model and put it in './' ('./vposer_v1_0/').

We also provide our pretrained model here

Training

After you generate the data. You can train the networks directly,

python train_subgoal.py
python train_route.py

Please train the posenet after you finished training routenet with your own pretrained routenet model,

python train_pose.py

Acknowledgement

This work was supported, in part, by grants from DARPA LwLL, NSF 1730158 CI-New: Cognitive Hardware and Software Ecosystem Community Infrastructure (CHASE-CI), NSF ACI-1541349 CC*DNI Pacific Research Platform, and gifts from Qualcomm and TuSimple. Part of our code is based on PROXE and it may help you with the dependencies and dataset parts as well. Many thanks!

License

Apache-2.0 License

Owner
My solutions for Stanford University course CS224W: Machine Learning with Graphs Fall 2021 colabs (GNN, GAT, GraphSAGE, GCN)

machine-learning-with-graphs My solutions for Stanford University course CS224W: Machine Learning with Graphs Fall 2021 colabs Course materials can be

Marko Njegomir 7 Dec 14, 2022
MXNet implementation for: Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution

Octave Convolution MXNet implementation for: Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution Imag

Meta Research 549 Dec 28, 2022
A minimalist implementation of score-based diffusion model

sdeflow-light This is a minimalist codebase for training score-based diffusion models (supporting MNIST and CIFAR-10) used in the following paper "A V

Chin-Wei Huang 89 Dec 20, 2022
we propose EfficientDerain for high-efficiency single-image deraining

EfficientDerain we propose EfficientDerain for high-efficiency single-image deraining Requirements python 3.6 pytorch 1.6.0 opencv-python 4.4.0.44 sci

Qing Guo 126 Dec 07, 2022
Code to reproduce the experiments from our NeurIPS 2021 paper " The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective"

Code To run: python runner.py new --save SAVE_NAME --data PATH_TO_DATA_DIR --dataset DATASET --model model_name [options] --n 1000 - train - t

Geoff Pleiss 5 Dec 12, 2022
Official PyTorch Implementation of Hypercorrelation Squeeze for Few-Shot Segmentation, arXiv 2021

Hypercorrelation Squeeze for Few-Shot Segmentation This is the implementation of the paper "Hypercorrelation Squeeze for Few-Shot Segmentation" by Juh

Juhong Min 165 Dec 28, 2022
PyTorch implementation for our paper "Deep Facial Synthesis: A New Challenge"

FSGAN Here is the official PyTorch implementation for our paper "Deep Facial Synthesis: A New Challenge". This project achieve the translation between

Deng-Ping Fan 32 Oct 10, 2022
Package for extracting emotions from social media text. Tailored for financial data.

EmTract: Extracting Emotions from Social Media Text Tailored for Financial Contexts EmTract is a tool that extracts emotions from social media text. I

13 Nov 17, 2022
The official implementation of VAENAR-TTS, a VAE based non-autoregressive TTS model.

VAENAR-TTS This repo contains code accompanying the paper "VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis". Sa

THUHCSI 138 Oct 28, 2022
LF-YOLO (Lighter and Faster YOLO) is used to detect defect of X-ray weld image.

This project is based on ultralytics/yolov3. LF-YOLO (Lighter and Faster YOLO) is used to detect defect of X-ray weld image. The related paper is avai

26 Dec 13, 2022
Jingju baseline - A baseline model of our project of Beijing opera script generation

Jingju Baseline It is a baseline of our project about Beijing opera script gener

midon 1 Jan 14, 2022
A simplistic and efficient pure-python neural network library from Phys Whiz with CPU and GPU support.

A simplistic and efficient pure-python neural network library from Phys Whiz with CPU and GPU support.

Manas Sharma 19 Feb 28, 2022
A dead simple python wrapper for darknet that works with OpenCV 4.1, CUDA 10.1

What Dead simple python wrapper for Yolo V3 using AlexyAB's darknet fork. Works with CUDA 10.1 and OpenCV 4.1 or later (I use OpenCV master as of Jun

Pliable Pixels 6 Jan 12, 2022
Özlem Taşkın 0 Feb 23, 2022
This is the repo for Uncertainty Quantification 360 Toolkit.

UQ360 The Uncertainty Quantification 360 (UQ360) toolkit is an open-source Python package that provides a diverse set of algorithms to quantify uncert

International Business Machines 207 Dec 30, 2022
An official PyTorch Implementation of Boundary-aware Self-supervised Learning for Video Scene Segmentation (BaSSL)

An official PyTorch Implementation of Boundary-aware Self-supervised Learning for Video Scene Segmentation (BaSSL)

Kakao Brain 72 Dec 28, 2022
🥇 LG-AI-Challenge 2022 1위 솔루션 입니다.

LG-AI-Challenge-for-Plant-Classification Dacon에서 진행된 농업 환경 변화에 따른 작물 병해 진단 AI 경진대회 에 대한 코드입니다. (colab directory에 코드가 잘 정리 되어있습니다.) Requirements python

siwooyong 10 Jun 30, 2022
这是一个yolo3-tf2的源码,可以用于训练自己的模型。

YOLOV3:You Only Look Once目标检测模型在Tensorflow2当中的实现 目录 性能情况 Performance 所需环境 Environment 文件下载 Download 训练步骤 How2train 预测步骤 How2predict 评估步骤 How2eval 参考资料

Bubbliiiing 68 Dec 21, 2022
[ICCV 2021] Relaxed Transformer Decoders for Direct Action Proposal Generation

RTD-Net (ICCV 2021) This repo holds the codes of paper: "Relaxed Transformer Decoders for Direct Action Proposal Generation", accepted in ICCV 2021. N

Multimedia Computing Group, Nanjing University 80 Nov 30, 2022
Orthogonal Over-Parameterized Training

The inductive bias of a neural network is largely determined by the architecture and the training algorithm. To achieve good generalization, how to effectively train a neural network is of great impo

Weiyang Liu 11 Apr 18, 2022