lmb-freiburg / Deeptam
Licence: gpl-3.0
DeepTAM: Deep Tracking and Mapping https://lmb.informatik.uni-freiburg.de/people/zhouh/deeptam/
Stars: ✭ 198
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Deeptam
Demon
DeMoN: Depth and Motion Network
Stars: ✭ 501 (+153.03%)
Mutual labels: cnn, structure-from-motion
Cnn Visualization
TensorFlow implementations of visualization of convolutional neural networks, such as Grad-Class Activation Mapping and guided back propagation
Stars: ✭ 194 (-2.02%)
Mutual labels: cnn
Freihand
A dataset for estimation of hand pose and shape from single color images.
Stars: ✭ 187 (-5.56%)
Mutual labels: cnn
Hand tracking samples
👋 👌 research codebase for depth-based hand pose estimation using dynamics based tracking and CNNs
Stars: ✭ 180 (-9.09%)
Mutual labels: cnn
Beauty Net
A simple, flexible, and extensible template for PyTorch. It's beautiful.
Stars: ✭ 190 (-4.04%)
Mutual labels: cnn
Sentence Classification
Sentence Classifications with Neural Networks
Stars: ✭ 177 (-10.61%)
Mutual labels: cnn
Lq Nets
LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks
Stars: ✭ 195 (-1.52%)
Mutual labels: cnn
Bilinear Cnn Tensorflow
This is an implementation of Bilinear CNN for fine grained visual recognition using TensorFlow.
Stars: ✭ 187 (-5.56%)
Mutual labels: cnn
Lidc nodule detection
lidc nodule detection with CNN and LSTM network
Stars: ✭ 187 (-5.56%)
Mutual labels: cnn
Speech Emotion Recognition
Speech emotion recognition implemented in Keras (LSTM, CNN, SVM, MLP) | 语音情感识别
Stars: ✭ 181 (-8.59%)
Mutual labels: cnn
Cnn Re Tf
Convolutional Neural Network for Multi-label Multi-instance Relation Extraction in Tensorflow
Stars: ✭ 190 (-4.04%)
Mutual labels: cnn
Hidden Two Stream
Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
Stars: ✭ 179 (-9.6%)
Mutual labels: cnn
Liteflownet2
A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization, TPAMI 2020
Stars: ✭ 195 (-1.52%)
Mutual labels: cnn
Tensorflow Tutorials
텐서플로우를 기초부터 응용까지 단계별로 연습할 수 있는 소스 코드를 제공합니다
Stars: ✭ 2,096 (+958.59%)
Mutual labels: cnn
Anime4k
A High-Quality Real Time Upscaler for Anime Video
Stars: ✭ 14,083 (+7012.63%)
Mutual labels: cnn
Depression Detect
Predicting depression from acoustic features of speech using a Convolutional Neural Network.
Stars: ✭ 187 (-5.56%)
Mutual labels: cnn
Deep Learning With Python
Deep learning codes and projects using Python
Stars: ✭ 195 (-1.52%)
Mutual labels: cnn
DeepTAM
DeepTAM is a learnt system for keyframe-based dense camera tracking and mapping.
If you use this code for research, please cite the following paper:
@InProceedings{ZUB18,
author = "H. Zhou and B. Ummenhofer and T. Brox",
title = "DeepTAM: Deep Tracking and Mapping",
booktitle = "European Conference on Computer Vision (ECCV)",
month = " ",
year = "2018",
url = "http://lmb.informatik.uni-freiburg.de/Publications/2018/ZUB18"
}
See the project page for the paper and other material.
Note: Currently we only provide deployment code.
Setup
Current version is tested on Ubuntu 16.04 and with Python3.
# install virtualenv manager (here we use pew)
pip3 install pew
# create virtualenv
pew new deeptam
# switch to virtualenv
pew in deeptam
# install tensorflow 1.4.0 with gpu
pip3 install tensorflow-gpu==1.4.0
# install some python modules
pip3 install minieigen
pip3 install scikit-image
# clone and build lmbspecialops (use branch deeptam)
git clone -b deeptam https://github.com/lmb-freiburg/lmbspecialops.git
LMBSPECIALOPS_DIR=$PWD/lmbspecialops
cd $LMBSPECIALOPS_DIR
mkdir build
cd build
cmake ..
make
# add lmbspecialops to your PYTHON_PATH
pew add $LMBSPECIALOPS_DIR/python
# clone deeptam git (currently only tracking code is available)
git clone https://github.com/lmb-freiburg/deeptam.git
DEEPTAM_DIR=$PWD/deeptam
# add deeptam_tracker to your PYTHON_PATH
pew add $DEEPTAM_DIR/tracking/python
# add deeptam_mapper to your PYTHON_PATH
pew add $DEEPTAM_DIR/mapping/python
Running tracking examples
# download example data
cd $DEEPTAM_DIR/tracking/data
./download_testdata.sh
# download weights
cd $DEEPTAM_DIR/tracking/weights
./download_weights.sh
The basic example shows how to use DeepTAM to track the camera within one keyframe:
# run a basic example
cd $DEEPTAM_DIR/tracking/examples
python3 example_basic.py
The advanced example shows how to track a video sequence with multiple keyframes:
# run an advanced example
cd $DEEPTAM_DIR/tracking/examples
python3 example_advanced_sequence.py
# or run without visualization for speedup
python3 example_advanced_sequence.py --disable_vis
Running mapping examples
# download weights
cd $DEEPTAM_DIR/mapping/weights
./download_weights.sh
# run the example
cd $DEEPTAM_DIR/mapping/examples
python3 mapping_test_deeptam.py
License
deeptam is under the GNU General Public License v3.0
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].