shawLyu / Hr Depth
Licence: mit
[AAAI 2021] HR-Depth : High Resolution Self-Supervised Depth Estimation
Stars: ✭ 116
Labels
Projects that are alternatives of or similar to Hr Depth
Lnpr book codes
Codes for Lecture Notes in Probabilistic Robotics
Stars: ✭ 115 (-0.86%)
Mutual labels: jupyter-notebook
Jwst
Python library for science observations from the James Webb Space Telescope
Stars: ✭ 115 (-0.86%)
Mutual labels: jupyter-notebook
Coursera reinforcement learning
Coursera Reinforcement Learning Specialization by University of Alberta & Alberta Machine Intelligence Institute
Stars: ✭ 114 (-1.72%)
Mutual labels: jupyter-notebook
Robust Physical Attack
Physical adversarial attack for fooling the Faster R-CNN object detector
Stars: ✭ 115 (-0.86%)
Mutual labels: jupyter-notebook
Machine Learning Demystified
A weekly workshop series at ITP to teach machine learning with a focus on deep learning
Stars: ✭ 114 (-1.72%)
Mutual labels: jupyter-notebook
Nlp Models Tensorflow
Gathers machine learning and Tensorflow deep learning models for NLP problems, 1.13 < Tensorflow < 2.0
Stars: ✭ 1,603 (+1281.9%)
Mutual labels: jupyter-notebook
Text generators
Python code for building a text generator using LSTMs.
Stars: ✭ 115 (-0.86%)
Mutual labels: jupyter-notebook
Ml19 20a
CS 771A: Introduction to Machine Learning, IIT Kanpur, 2019-20-autumn offering
Stars: ✭ 115 (-0.86%)
Mutual labels: jupyter-notebook
Gutenberg Poetry Corpus
A corpus of poetry from Project Gutenberg
Stars: ✭ 115 (-0.86%)
Mutual labels: jupyter-notebook
Traffic Signs
Building a CNN based traffic signs classifier.
Stars: ✭ 115 (-0.86%)
Mutual labels: jupyter-notebook
Quantum Algorithms Tutorials
Tutorials for Quantum Algorithms with Qiskit implementations.
Stars: ✭ 115 (-0.86%)
Mutual labels: jupyter-notebook
Flotilla
Reproducible machine learning analysis of gene expression and alternative splicing data
Stars: ✭ 115 (-0.86%)
Mutual labels: jupyter-notebook
Cadl
ARCHIVED: Contains historical course materials/Homework materials for the FREE MOOC course on "Creative Applications of Deep Learning w/ Tensorflow" #CADL
Stars: ✭ 1,478 (+1174.14%)
Mutual labels: jupyter-notebook
A Nice Mc
Code for "A-NICE-MC: Adversarial Training for MCMC"
Stars: ✭ 115 (-0.86%)
Mutual labels: jupyter-notebook
Emp
Code repository of the Earth Microbiome Project.
Stars: ✭ 115 (-0.86%)
Mutual labels: jupyter-notebook
Dat8
General Assembly's 2015 Data Science course in Washington, DC
Stars: ✭ 1,516 (+1206.9%)
Mutual labels: jupyter-notebook
Bayareadlschool
Slides and exercises for the Theano tutorial at the Deep Learning School in Stanford, September 24-25, 2016
Stars: ✭ 115 (-0.86%)
Mutual labels: jupyter-notebook
HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation
This is the official implementation for training and testing depth estimation using the model proposed in
HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation
Xiaoyang Lyu, Liang Liu, Mengmeng Wang, Xin Kong, Lina Liu, Yong Liu*, Xinxin Chen and Yi Yuan.
This paper has been accepted by AAAI 2021.
Note: We temporarily release the evaluation version and some pretrained models of our paper. The training codes are modified according to Monodepth2, and we will release them soon.
Update
2021.1.27
- The training code will be released around the beginning of the March.
- For re-implementing HR-Depth, you can clone Monodepth2 and simply replace the
DepthDecoderwithHRDepthDecoder. Our parameter settings are exactly the same as Monodepth2. - In our paper, we wrote the initial learning rate wrong. It should be 1e-4, not 1e-3. We will fix this mistake in the final version. Thanks for someone pointing out our problem.
Quantitative Results
HR-Depth Results
Lite-HR-Depth Results
Usage
Requirements
Assuming a fresh Anaconda distribution, you can install the dependencies with:
conda install pytorch=1.5.0 torchvision=0.6.0 -c pytorch
conda install opencv=4.2
pip install scipy=1.4.1
Pretrained Model
We provided pretrained model as follow:
| Model Name | Resolution | Dataset | Supervision | Abs_Rel | $\delta<1.25$ | $\delta<1.25^2$ | $\delta<1.25^3$ |
|---|---|---|---|---|---|---|---|
| HR_Depth_CS_K_MS_$640\times192$ | $640\times192$ | CS+K | MS | 0.104 | 0.893 | 0.964 | 0.983 |
| HR_Depth_K_MS_$1024\times320$ | $1024\times320$ | K | MS | 0.101 | 0.899 | 0.966 | 0.983 |
| HR_Depth_K_M_$1280\times384$ | $1280\times384$ | K | M | 0.104 | 0.894 | 0.966 | 0.984 |
| Lite_HR_Depth_K_T_$1280\times384$ | $1280\times384$ | K | T | 0.104 | 0.893 | 0.967 | 0.985 |
KITTI training data
You can download the entire KITTI_raw dataset by running:
wget -i splits/kitti_archives_to_download.txt -P kitti_data/
Then unzip with
cd kitti_data
unzip "*.zip"
cd ..
Warning: The size of this dataset is about 175GB, so make sure you have enough space to unzip them.
KITTI evaluation
--data_path: path of KITTI dataset
--load_weights_folder: path of models
--HR_Depth: inference by HR-Depth
--Lite_HR_Depth: inference by Lite-HR-Depth
To prepare the ground truth depth maps run:
python export_gt_depth.py --data_path ./kitti_RAW
assuming that you have placed the KITTI RAW dataset in the default location of ./kitti_data.
For HR-Depth:
python evaluate_depth.py --data_path ./kitti_RAW --load_weights_folder ./models/HR_Depth_CS_K_MS_640x192 --HR_Depth
python evaluate_depth.py --data_path ./kitti_RAW --load_weights_folder ./models/HR_Depth_K_M_1280x384 --HR_Depth
For Lite-HR-Depth:
python evaluate_depth.py --data_path ./kitti_RAW --load_weights_folder ./models/Lite_HR_Depth_K_T_1280x384 --Lite_HR_Depth
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].