Deep Compression for Dense Point Cloud Maps.

Overview

DEPOCO

This repository implements the algorithms described in our paper Deep Compression for Dense Point Cloud Maps.

How to get started (using Docker)

Dependenices nvida-docker

Install nvida-docker and follow these instructions

Data

You can download the dataset from here and link the dataset to the docker container by configuring the Makefile

DATASETS=<path-to-your-data>

Building the docker container

For building the Docker Container simply run

make build

in the root directory.

Running the Code

The first step is to run the docker container:

make run

The following commands assume to be run inside the docker container.

Training

For training a network we first have to create the config file with all the parameters. An example of this can be found in /depoco/config/depoco.yaml. Make sure to give each config file a unique experiment_id: ... to not override previous models. To train the network simply run

python3 trainer -cfg <path-to-your-config>

Evaluation

Evaluating the network on the test set can be done by:

python3 evaluate.py -cfg <path-to-your-config>

All results will be saved in a dictonary.

Plotting the results

We can plot the quantitative results e.g. by using Jupyter-Lab. An example of this is provided in depoco/notebooks/visualize.ipynb. Jupyter-Lab can be started in the Docker container by:

jupyter-lab  --ip 0.0.0.0 --no-browser --allow-root

The 8888 port is forwarded which allows us to use it as if it would be on the host machine.

Pretrained models

The config files and the pretrained weights of our models are stored in depoco/network_files/eX/. The results can be inspected by the jupyter notebook depoco/notebooks/visualize.ipynb.

How to get started (without Docker)

Installation

A list of all dependencies and install instructions can be derived from the Dockerfile.

Running the code

After installation the training and evaluation can be run as explained before.

Qualitative Results

Plotting the point clouds using open3d can be done by

pyhon3 evaluate -cfg <path-to-your-config>

This can not be done in the docker container and thus requires the installation on the local machine.

Citation

If you use this library for any academic work, please cite the original paper.

@article{wiesmann2021ral,
author = {L. Wiesmann and A. Milioto and X. Chen and C. Stachniss and J. Behley},
title = {{Deep Compression for Dense Point Cloud Maps}},
journal = {IEEE Robotics and Automation Letters (RA-L)},
volume = 6,
issue = 2,
pages = {2060-2067},
doi = {10.1109/LRA.2021.3059633},
year = 2021
}
Owner
Photogrammetry & Robotics Bonn
Photogrammetry & Robotics Lab at the University of Bonn
Photogrammetry & Robotics Bonn
Styled Handwritten Text Generation with Transformers (ICCV 21)

⚡ Handwriting Transformers [PDF] Ankan Kumar Bhunia, Salman Khan, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan & Mubarak Shah Abstract: We

Ankan Kumar Bhunia 85 Dec 22, 2022
Code and real data for the paper "Counterfactual Temporal Point Processes", available at arXiv.

counterfactual-tpp This is a repository containing code and real data for the paper Counterfactual Temporal Point Processes. Pre-requisites This code

Networks Learning 11 Dec 09, 2022
Detectron2-FC a fast construction platform of neural network algorithm based on detectron2

What is Detectron2-FC Detectron2-FC a fast construction platform of neural network algorithm based on detectron2. We have been working hard in two dir

董晋宗 9 Jun 06, 2022
Final project code: Implementing BicycleGAN, for CIS680 FA21 at University of Pennsylvania

680 Final Project: BicycleGAN Haoran Tang Instructions 1. Training To train the network, please run train.py. Change hyper-parameters and folder paths

Haoran Tang 0 Apr 22, 2022
PyExplainer: A Local Rule-Based Model-Agnostic Technique (Explainable AI)

PyExplainer PyExplainer is a local rule-based model-agnostic technique for generating explanations (i.e., why a commit is predicted as defective) of J

AI Wizards for Software Management (AWSM) Research Group 14 Nov 13, 2022
"Projelerle Yapay Zeka Ve Bilgisayarlı Görü" Kitabımın projeleri

"Projelerle Yapay Zeka Ve Bilgisayarlı Görü" Kitabımın projeleri Bu Github Reposundaki tüm projeler; kaleme almış olduğum "Projelerle Yapay Zekâ ve Bi

Ümit Aksoylu 4 Aug 03, 2022
A deep-learning pipeline for segmentation of ambiguous microscopic images.

Welcome to Official repository of deepflash2 - a deep-learning pipeline for segmentation of ambiguous microscopic images. Quick Start in 30 seconds se

Matthias Griebel 39 Dec 19, 2022
Speckle-free Holography with Partially Coherent Light Sources and Camera-in-the-loop Calibration

Speckle-free Holography with Partially Coherent Light Sources and Camera-in-the-loop Calibration Project Page | Paper Yifan Peng*, Suyeon Choi*, Jongh

Stanford Computational Imaging Lab 19 Dec 11, 2022
Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation

Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation By Qiang Zhou*, Zilong Huang*, Lichao Huang, Han Shen, Yon

Forest 117 Apr 01, 2022
Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics

[AAAI2022] Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics Overall pipeline of OCN. Paper Link: [arXiv] [AAAI

13 Nov 21, 2022
The repo for the paper "I3CL: Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection".

I3CL: Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection Updates | Introduction | Results | Usage | Citation |

33 Jan 05, 2023
Implementation of Vaswani, Ashish, et al. "Attention is all you need."

Attention Is All You Need Paper Implementation This is my from-scratch implementation of the original transformer architecture from the following pape

Brando Koch 195 Dec 30, 2022
Flexible-CLmser: Regularized Feedback Connections for Biomedical Image Segmentation

Flexible-CLmser: Regularized Feedback Connections for Biomedical Image Segmentation The skip connections in U-Net pass features from the levels of enc

Boheng Cao 1 Dec 29, 2021
[ICCV' 21] "Unsupervised Point Cloud Pre-training via Occlusion Completion"

OcCo: Unsupervised Point Cloud Pre-training via Occlusion Completion This repository is the official implementation of paper: "Unsupervised Point Clou

Hanchen 204 Dec 24, 2022
A hyperparameter optimization framework

Optuna: A hyperparameter optimization framework Website | Docs | Install Guide | Tutorial Optuna is an automatic hyperparameter optimization software

7.4k Jan 04, 2023
Code and Resources for the Transformer Encoder Reasoning Network (TERN)

Transformer Encoder Reasoning Network Code for the cross-modal visual-linguistic retrieval method from "Transformer Reasoning Network for Image-Text M

Nicola Messina 53 Dec 30, 2022
STBP is a way to train SNN with datasets by Backward propagation.

Spiking neural network (SNN), compared with depth neural network (DNN), has faster processing speed, lower energy consumption and more biological interpretability, which is expected to approach Stron

Ling Zhang 18 Dec 09, 2022
Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks

MGANs Training & Testing code (torch), pre-trained models and supplementary materials for "Precomputed Real-Time Texture Synthesis with Markovian Gene

290 Nov 15, 2022
Tutorial page of the Climate Hack, the greatest hackathon ever

Tutorial page of the Climate Hack, the greatest hackathon ever

UCL Artificial Intelligence Society 12 Jul 02, 2022
Code for the ECCV2020 paper "A Differentiable Recurrent Surface for Asynchronous Event-Based Data"

A Differentiable Recurrent Surface for Asynchronous Event-Based Data Code for the ECCV2020 paper "A Differentiable Recurrent Surface for Asynchronous

Marco Cannici 21 Oct 05, 2022