All Projects → knorth55 → chainer-dense-fusion

knorth55 / chainer-dense-fusion

Licence: MIT License
Chainer implementation of Dense Fusion

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to chainer-dense-fusion

chainer-fcis
[This project has moved to ChainerCV] Chainer Implementation of Fully Convolutional Instance-aware Semantic Segmentation
Stars: ✭ 45 (+114.29%)
Mutual labels:  chainer, inference, chainercv
Chainer Pose Proposal Net
Chainer implementation of Pose Proposal Networks
Stars: ✭ 119 (+466.67%)
Mutual labels:  chainer, pose-estimation
Chainercv
ChainerCV: a Library for Deep Learning in Computer Vision
Stars: ✭ 1,463 (+6866.67%)
Mutual labels:  chainer, chainercv
chainer-sort
Simple, Online, Realtime Tracking of Multiple Objects (SORT) implementation for Chainer and ChainerCV.
Stars: ✭ 20 (-4.76%)
Mutual labels:  chainer, chainercv
sc depth pl
Pytorch Lightning Implementation of SC-Depth (V1, V2...) for Unsupervised Monocular Depth Estimation.
Stars: ✭ 86 (+309.52%)
Mutual labels:  pose-estimation
pyinfer
Pyinfer is a model agnostic tool for ML developers and researchers to benchmark the inference statistics for machine learning models or functions.
Stars: ✭ 19 (-9.52%)
Mutual labels:  inference
Multi-Person-Pose-using-Body-Parts
No description or website provided.
Stars: ✭ 41 (+95.24%)
Mutual labels:  pose-estimation
efficient softmax
BlackOut and Adaptive Softmax for language models by Chainer
Stars: ✭ 12 (-42.86%)
Mutual labels:  chainer
MobileNetV2-PoseEstimation
Tensorflow based Fast Pose estimation. OpenVINO, Tensorflow Lite, NCS, NCS2 + Python.
Stars: ✭ 99 (+371.43%)
Mutual labels:  pose-estimation
neural style synthesizer
No description or website provided.
Stars: ✭ 15 (-28.57%)
Mutual labels:  chainer
LEMO
Official Pytorch implementation for 2021 ICCV paper "Learning Motion Priors for 4D Human Body Capture in 3D Scenes" and trained models / data
Stars: ✭ 149 (+609.52%)
Mutual labels:  pose-estimation
awesome-6d-object
Awesome work on object 6 DoF pose estimation
Stars: ✭ 252 (+1100%)
Mutual labels:  pose-estimation
FashionAI-Keypoint
fashionAI clothes keypoint detection
Stars: ✭ 19 (-9.52%)
Mutual labels:  pose-estimation
DSTC6-End-to-End-Conversation-Modeling
DSTC6: End-to-End Conversation Modeling Track
Stars: ✭ 56 (+166.67%)
Mutual labels:  chainer
forestError
A Unified Framework for Random Forest Prediction Error Estimation
Stars: ✭ 23 (+9.52%)
Mutual labels:  inference
MSPN
Multi-Stage Pose Network
Stars: ✭ 321 (+1428.57%)
Mutual labels:  pose-estimation
HRFormer
This is an official implementation of our NeurIPS 2021 paper "HRFormer: High-Resolution Transformer for Dense Prediction".
Stars: ✭ 357 (+1600%)
Mutual labels:  pose-estimation
Primer-MotionCapture
A Primer on Motion Capture with Deep Learning:Principles, Pitfalls and Perspectives
Stars: ✭ 19 (-9.52%)
Mutual labels:  pose-estimation
chainer-ADDA
Adversarial Discriminative Domain Adaptation in Chainer
Stars: ✭ 24 (+14.29%)
Mutual labels:  chainer
Fast Stacked Hourglass Network OpenVino
A fast stacked hourglass network for human pose estimation on OpenVino
Stars: ✭ 52 (+147.62%)
Mutual labels:  pose-estimation

chainer-dense-fusion

Build Status

This is Chainer implementation of DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion.

Original PyTorch repository is j96w/DenseFusion.

Requirement

Installation

We recommend to use Anacoda.

# Requirement installation
conda create -n dense-fusion python=3.6
source activate dense-fusion 
pip install opencv-python
pip install cupy

# Installation
git clone https://github.com/knorth55/chainer-dense-fusion.git
cd chainer-dense-fusion/
pip install -e .

Inference

cd examples/dense_fusion/
python demo.py --random

TODO

  • YCB Video Dataset
    • Add estimator inference script.
    • Add refiner inference script.
    • Add training script.
    • Reproduce original accuracy.

LICENSE

MIT LICENSE

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].