GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → Lotayou → Densebody_pytorch

Lotayou / Densebody_pytorch

Licence: gpl-3.0
PyTorch implementation of CloudWalk's recent work DenseBody

Programming Languages

python
139335 projects - #7 most used programming language

Labels

pytorchpose-estimation3d-reconstruction

Projects that are alternatives of or similar to Densebody pytorch

aistplusplus api
API to support AIST++ Dataset: https://google.github.io/aistplusplus_dataset
Stars: ✭ 277 (-26.72%)
Mutual labels:  3d-reconstruction, pose-estimation
ICON
ICON: Implicit Clothed humans Obtained from Normals (CVPR 2022)
Stars: ✭ 641 (+69.58%)
Mutual labels:  3d-reconstruction, pose-estimation
handobjectconsist
[cvpr 20] Demo, training and evaluation code for joint hand-object pose estimation in sparsely annotated videos
Stars: ✭ 100 (-73.54%)
Mutual labels:  3d-reconstruction, pose-estimation
Awesome Action Recognition
A curated list of action recognition and related area resources
Stars: ✭ 3,202 (+747.09%)
Mutual labels:  pose-estimation
Surfelmeshing
Real-time surfel-based mesh reconstruction from RGB-D video.
Stars: ✭ 278 (-26.46%)
Mutual labels:  3d-reconstruction
Layoutnet
Torch implementation of our CVPR 18 paper: "LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image"
Stars: ✭ 334 (-11.64%)
Mutual labels:  3d-reconstruction
Kimera Semantics
Real-Time 3D Semantic Reconstruction from 2D data
Stars: ✭ 368 (-2.65%)
Mutual labels:  3d-reconstruction
Convolutional occupancy networks
[ECCV'20] Convolutional Occupancy Networks
Stars: ✭ 276 (-26.98%)
Mutual labels:  3d-reconstruction
Libfaceid
libfaceid is a research framework for prototyping of face recognition solutions. It seamlessly integrates multiple detection, recognition and liveness models w/ speech synthesis and speech recognition.
Stars: ✭ 354 (-6.35%)
Mutual labels:  pose-estimation
Semantic slam
Real time semantic slam in ROS with a hand held RGB-D camera
Stars: ✭ 317 (-16.14%)
Mutual labels:  3d-reconstruction
Monoport
Volumetric Human Teleportation (SIGGRAPH 2020 Real-Time Live) Monocular Real-Time Volumetric Performance Capture(ECCV 2020)
Stars: ✭ 296 (-21.69%)
Mutual labels:  3d-reconstruction
Mspn
Multi-Stage Pose Network
Stars: ✭ 283 (-25.13%)
Mutual labels:  pose-estimation
Pose Residual Network
Code for the Pose Residual Network introduced in 'MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network (ECCV 2018)' paper
Stars: ✭ 337 (-10.85%)
Mutual labels:  pose-estimation
Tf.fashionai
Full pipeline for TianChi FashionAI clothes keypoints detection compitetion in TensorFlow
Stars: ✭ 280 (-25.93%)
Mutual labels:  pose-estimation
Nerf pl
NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning
Stars: ✭ 362 (-4.23%)
Mutual labels:  3d-reconstruction
Pose Residual Network Pytorch
Code for the Pose Residual Network introduced in 'MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network' paper https://arxiv.org/abs/1807.04067
Stars: ✭ 277 (-26.72%)
Mutual labels:  pose-estimation
Pytorch Human Pose Estimation
Implementation of various human pose estimation models in pytorch on multiple datasets (MPII & COCO) along with pretrained models
Stars: ✭ 346 (-8.47%)
Mutual labels:  pose-estimation
Star
ECCV2020 - Official code repository for the paper : STAR - A Sparse Trained Articulated Human Body Regressor
Stars: ✭ 296 (-21.69%)
Mutual labels:  pose-estimation
Intrinsic3d
Intrinsic3D - High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting (ICCV 2017)
Stars: ✭ 297 (-21.43%)
Mutual labels:  3d-reconstruction
Poseflow
PoseFlow: Efficient Online Pose Tracking (BMVC'18)
Stars: ✭ 330 (-12.7%)
Mutual labels:  pose-estimation
View All Similar Projects ➔

densebody_pytorch

PyTorch implementation of CloudWalk's recent paper DenseBody.

Note: For most recent updates, please check out the dev branch.

Update on 20190613 A toy dataset has been released to facilitate the reproduction of this project. checkout PREPS.md for details.

Update on 20190826 A pre-trained model (Encoder/Decoder) has been released to facilitate the reproduction of this project.

paper teaser

Reproduction results

Here is the reproduction result (left: input image; middle: ground truth UV position map; right: estimated UV position map)

Update Notes

  • SMPL official UV map is now supported! Please checkout PREPS.md for details.
  • Code reformating complete! Please refer to data_utils/UV_map_generator.py for more details.
  • Thanks Raj Advani for providing new hand crafted UV maps!

Training Guidelines

Please follow the instructions PREPS.md to prepare your training dataset and UV maps. Then run train.sh or nohup_train.sh to begin training.

Customizations

To train with your own UV map, checkout UV_MAPS.md for detailed instructions.

To explore different network architectures, checkout NETWORKS.md for detailed instructions.

TODO List

  • [x] Creating ground truth UV position maps for Human36m dataset.

    • [x] 20190329 Finish UV data processing.
    • [x] 20190331 Align SMPL mesh with input image.
    • [x] 20190404 Data washing: Image resize to 256*256 and 2D annotation compensation.
    • [x] 20190411 Generate and save UV position map.
      • [x] radvani Hand parsed new 3D UV data
      • [x] Validity checked with minor artifacts (see results below)
      • [x] Making UV_map generation module a separate class.
    • [x] 20190413 Prepare ground truth UV maps for washed dataset.
    • [x] 20190417 SMPL official UV map supported!
    • [x] 20190613 A testing toy dataset has been released!

  • [x] Prepare baseline model training

    • [x] 20190414 Network design, configs, trainer and dataloader
    • [x] 20190414 Baseline complete with first-hand results. Something issue still needs to be addressed.
    • [x] 20190420 Testing with different UV maps.

Authors

Lingbo Yang(Lotayou): The owner and maintainer of this repo.

Raj Advani(radvani): Provide several hand-crafted UV maps and many constructive feedbacks.

Citation

Please consider citing the following paper if you find this project useful.

DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Image

Acknowledgements

The network training part is inspired by BicycleGAN

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].