SlideShare a Scribd company logo
1 of 25
Download to read offline
Deep$Learning$
on
3D$Point$Clouds
SK#Reddy#
Chief#Product#Officer#AI
skreddy99
skreddy99
Confidential2
ImageNet(Large(Scale(Visual(Recognition(Challenge((ILSVRC)(winners
Confidential3 https://arxiv.org/pdf/1808.01462.pdf
Confidential4 https://arxiv.org/pdf/1808.01462.pdf
Confidential5
O"CNN%&2017
https://arxiv.org/pdf/1712.01537.pdf
Left:<the<original<3D<shape.<Middle:<the<voxelized 3D<
shape.<Right:<the<octree<representation<with<normals
sampled<at<the<finest<leaf<octants
2D<quadtree<illustration<of<octree<structure
Confidential6
OctNet&'2017
https://arxiv.org/pdf/1611.05009.pdf
Network=Architecture=Semantic=3D=Point=Cloud=
Labeling
Hybrid=GridKOctree=Data=Structure.=This=example=illustrates=a=
hybrid=gridKoctree=consisting=of=8=shallow=octrees=indicated=by=
different=colors.=Using=2=shallow=octrees=in=each=dimension=
with=a=maximum=depth=of=3=leads=to=a=total=resolution=of========
voxels
Bit=Representation.=Shallow=octrees=can=be=efficiently=encoded=
using=bitKstrings.=Here,=the=bitKstring=1=01010000=00000000=
01010000=00000000=01010000=0...=defines=the=octree=in=(a).=The=
corresponding=tree=is=shown=in=(b).=The=color=of=the=voxels=
corresponds=to=the=split=level
Confidential7
PointNet()2017
https://arxiv.org/pdf/1612.00593.pdf
Confidential8
Deep$Kd'Network.$2017
https://arxiv.org/pdf/1704.01222.pdf
A<kd>tree<built<on<the<point<cloud<of<eight<points<(left),<
and<the<associated<Kd>network<built<for<classification<
(right)
The<architecture<for<parts<segmentation<(individual<point<classification)<
for<the<point<cloud
Confidential9
PointNet++)*2017
https://arxiv.org/pdf/1706.02413.pdf
(a) MultiAscaleCgroupingC(MSG)FC
(b) MultiresolutionCgroupingC(MRG)
MNISTCdigitCclassification
Confidential10
SPLATNet)*2018*
https://arxiv.org/pdf/1802.08275.pdf
Bilateral*Convolution*Layer Left:<splatting<the<input<points<(orange)<onto<
the<lattice<corners<(black)C<Middle:<The<extent<of<a<filter<on<the<lattice<with<a<s<=<2<
neighborhood<(white<circles),<for<reference<we<show<a<Gaussian<filter,<with<its<
values<color<coded.<The<general<case<has<a<free<scalar/vector<parameter<per<
circle.<Right:<The<result<of<the<convolution<at<the<lattice<corners<(black)<is<projected<
back<to<the<output<points<(blue).<
Confidential11
MRTNet'(2018
https://arxiv.org/pdf/1807.03520.pdf
Confidential12
SqueezeSeg:.CNNs.with.Recurrent.CRF.for.Real8Time.Road8
Object.Segmentation.from.3D.LiDAR.Point.CloudE.2017
https://arxiv.org/pdf/1710.07368.pdf
Conditional.Random.Field.(CRF).as.an.RNN.layer
Confidential13
PointSeg-.Sep.2018
https://arxiv.org/pdf/1807.06288.pdf
The.pipeline.of.PointSeg..Raw.LiDAR.point.cloud.is.projected.to.a.multichannel.range.
image..After.the.network.processing,.the.predicted.pointLwise.label.will.be.projected.back.
to.the.original.space.
Source.code:.https://github.com/ywangeq/PointSeg
Confidential14
LMNet:.Real0time.Multiclass.Object.Detection.on.CPU.using.3D.LiDAR@.2018
https://arxiv.org/pdf/1805.04902.pdf
IMPLEMENTED.DILATED.LAYERS
Confidential15
DeLS%3D:.Deep.Localization.and.
Segmentation.with.a.3D.Semantic.Map;.2018
https://arxiv.org/pdf/1805.04949.pdf
Confidential16
Spherical CNN for/3D/Point/Clouds5/2018
https://arxiv.org/pdf/1805.07872.pdf
Classification/performance/on/ModelNetszz
Confidential17
https://arxiv.org/pdf/1808.06840.pdf
Example(result(of(our(FCPN(on(semantic(voxel(labeling(and(captioning(on(an(Tango(3D(
reconstruction(/(point(cloud:((a)(3D(reconstruction((not(used),((b)(Input(point(cloud((c)(Output(
semantic(voxel(prediction.(
Visualization(of(the(semantic(segmentation(on((a)(a(depth(image,((b)(a(2.4m×2.4m×2.4m(partial(
reconstruction((c)(an(entire(reconstruction(of(a(hotel(suite.(Please(note(that(each(of(these(outputs(
are(predicted(in(a(single(shot(from(the(same(network(trained(with(2.4m(× 2.4m(× 2.4m(volumes(
Fully%Convolutional-Point-Network-Architecture Aug=2018=
(Source=code:=Not=yetD=https://github.com/drethage/fullyGconvolutionalGpointGnetwork)
Confidential18
Data$sets
• ScanNet:2Indoor2Scenes
• ShapeNet:23D2shapes
• Princeton2ModelNet
• KITTI2(Code2available2for2some)
• Pascal3D+2(….in2the2wild)
• Pascal2VOC
• SUNCG2(room2models)
• SceneNet (RGBMD2room2models)
• CV2Lab2datasets2with2Code2
(http://cvgl.stanford.edu/resources.html)
• Collective2Activity2Dataset2(old)
• Monocular2Multiview2Object2Tracking2with2
3D2Aspect2Parts2(???)
• Stanford22DM3DMSemantics2Dataset2(2DM
3DMS)2(**)
• Stanford2Drone2Dataset
• ObjectNet3D
List$of$datasets:
1.2http://clickdamage.com/sourcecode/cv_datasets.php
Other$Data$sets
• TOSCA2(nonMrigid2dataset)
• FAUST2(highMres2human2scans)
• SUN3D
• NYC3DCars
• LabelMe3D2(old2dataset)
• CVLab (MultiMview2car2dataset)
• MIT2Street2Scenes
• Daimler2Pedestrian2Datasets
• Caltech2Pedestrian2Detection2Benchmark
• Robust2MultiMPerson2Tracking2from2Mobile2Platforms
• FlyingThings3D2(Synthetic)
• BU4DFE23D2
Confidential19
PVNet:"A"Joint"Network"of"Point"Cloud"and"Multi6View"for"
3D"Shape"Recognition"(Aug"2018)
Confidential20 https://arxiv.org/pdf/1806.01411.pdf
FlowNet3D:;Scene;Flow;in;3D;PCs(June;2018);
Confidential21
YOLO3D Aug02018
Sample0of0the0output0shown0in03D0and0projected0on0the0top0view0map0
Confidential22
PointFlowNet 3D.Scene.Flow.Estimation.from.PCs.(Sep.2018)
https://arxiv.org/pdf/1806.02170.pdf
Confidential23
Point&Cloud&Library Modules
Confidential24
https://github.com/kzampog/cilantro;
Cilantro
library;for;point;cloud;data;processing;
Bundled;with:;
• nanoflann (for;fast;kdAtree;queries);
• Spectra;(ARPACKAinspired;library;for;large;
scale;eigen;decompositions;
• Qhull (for;convex;hull;and;halfA space;
intersection;computations);
• tinyply (for;PLY;format;geometry;I/O);
• External;dependencies:;
• Eigen;(linear;algebra;library);
• Pangolin;(lightweight;OpenGL;viewport;
manager;and;video;I/O;abstraction;library)
Confidential25
Thank&you
SK&Reddy
Chief&Product&Officer&AI
skreddy99
skreddy99

More Related Content

Similar to Making sense from 3D Point Clouds

Ajax Performance Tuning and Best Practices
Ajax Performance Tuning and Best PracticesAjax Performance Tuning and Best Practices
Ajax Performance Tuning and Best Practices
Doris Chen
 

Similar to Making sense from 3D Point Clouds (20)

D3.js: Data Visualization for the Web
D3.js: Data Visualization for the Web D3.js: Data Visualization for the Web
D3.js: Data Visualization for the Web
 
Overview of the DDS-XRCE specification
Overview of the DDS-XRCE specificationOverview of the DDS-XRCE specification
Overview of the DDS-XRCE specification
 
[CSSDevConf] Adaptive Images in Responsive Web Design 2014
[CSSDevConf] Adaptive Images in Responsive Web Design 2014[CSSDevConf] Adaptive Images in Responsive Web Design 2014
[CSSDevConf] Adaptive Images in Responsive Web Design 2014
 
Sitecore 9 xConnect and Marketing Automation
Sitecore 9 xConnect and Marketing AutomationSitecore 9 xConnect and Marketing Automation
Sitecore 9 xConnect and Marketing Automation
 
DataStax: Enabling Search in your Cassandra Application with DataStax Enterprise
DataStax: Enabling Search in your Cassandra Application with DataStax EnterpriseDataStax: Enabling Search in your Cassandra Application with DataStax Enterprise
DataStax: Enabling Search in your Cassandra Application with DataStax Enterprise
 
DSL101
DSL101DSL101
DSL101
 
Ajax Performance Tuning and Best Practices
Ajax Performance Tuning and Best PracticesAjax Performance Tuning and Best Practices
Ajax Performance Tuning and Best Practices
 
DDS-Security Interoperability Demo - March 2018
DDS-Security Interoperability Demo - March 2018DDS-Security Interoperability Demo - March 2018
DDS-Security Interoperability Demo - March 2018
 
What can Bioinformaticians learn from YouTube?
What can Bioinformaticians learn from YouTube?What can Bioinformaticians learn from YouTube?
What can Bioinformaticians learn from YouTube?
 
SparkR - Play Spark Using R (20160909 HadoopCon)
SparkR - Play Spark Using R (20160909 HadoopCon)SparkR - Play Spark Using R (20160909 HadoopCon)
SparkR - Play Spark Using R (20160909 HadoopCon)
 
Apache Ignite - Distributed SQL Database Capabilities
Apache Ignite - Distributed SQL Database CapabilitiesApache Ignite - Distributed SQL Database Capabilities
Apache Ignite - Distributed SQL Database Capabilities
 
JavaOne 2016: Code Generation with JavaCompiler for Fun, Speed and Business P...
JavaOne 2016: Code Generation with JavaCompiler for Fun, Speed and Business P...JavaOne 2016: Code Generation with JavaCompiler for Fun, Speed and Business P...
JavaOne 2016: Code Generation with JavaCompiler for Fun, Speed and Business P...
 
Our application got popular and now it breaks
Our application got popular and now it breaksOur application got popular and now it breaks
Our application got popular and now it breaks
 
Our application got popular and now it breaks
Our application got popular and now it breaksOur application got popular and now it breaks
Our application got popular and now it breaks
 
Jose Selvi - Side-Channels Uncovered [rootedvlc2018]
Jose Selvi - Side-Channels Uncovered [rootedvlc2018]Jose Selvi - Side-Channels Uncovered [rootedvlc2018]
Jose Selvi - Side-Channels Uncovered [rootedvlc2018]
 
Render Caching for Drupal 8
Render Caching for Drupal 8Render Caching for Drupal 8
Render Caching for Drupal 8
 
MongoDB .local Paris 2020: Les bonnes pratiques pour travailler avec les donn...
MongoDB .local Paris 2020: Les bonnes pratiques pour travailler avec les donn...MongoDB .local Paris 2020: Les bonnes pratiques pour travailler avec les donn...
MongoDB .local Paris 2020: Les bonnes pratiques pour travailler avec les donn...
 
XJDF for Developers
XJDF for DevelopersXJDF for Developers
XJDF for Developers
 
Graphs for Genealogists
Graphs for GenealogistsGraphs for Genealogists
Graphs for Genealogists
 
A Cassandra + Solr + Spark Love Triangle Using DataStax Enterprise
A Cassandra + Solr + Spark Love Triangle Using DataStax EnterpriseA Cassandra + Solr + Spark Love Triangle Using DataStax Enterprise
A Cassandra + Solr + Spark Love Triangle Using DataStax Enterprise
 

More from SK Reddy

More from SK Reddy (20)

Finding the right Machine Learning method for predictive modeling
Finding the right Machine Learning method for predictive modelingFinding the right Machine Learning method for predictive modeling
Finding the right Machine Learning method for predictive modeling
 
AI to open more doors in Personal Finance Management (PFM)
AI to open more doors in Personal Finance Management (PFM)AI to open more doors in Personal Finance Management (PFM)
AI to open more doors in Personal Finance Management (PFM)
 
The wonders of big data processing using Deep Learning in Brazil Live 15 sep ...
The wonders of big data processing using Deep Learning in Brazil Live 15 sep ...The wonders of big data processing using Deep Learning in Brazil Live 15 sep ...
The wonders of big data processing using Deep Learning in Brazil Live 15 sep ...
 
How organizations can get ready for ai
How organizations can get ready for aiHow organizations can get ready for ai
How organizations can get ready for ai
 
Practical implementation of AI solutions for Smart Cities
Practical implementation of AI solutions for Smart Cities Practical implementation of AI solutions for Smart Cities
Practical implementation of AI solutions for Smart Cities
 
Recommender systems
Recommender systems Recommender systems
Recommender systems
 
How recommender systems work
How recommender systems work How recommender systems work
How recommender systems work
 
In search of better deep Recommender Systems
In search of better deep Recommender Systems In search of better deep Recommender Systems
In search of better deep Recommender Systems
 
Deep Learning (DL) Solutions for Smart City use cases
Deep Learning (DL) Solutions for Smart City use casesDeep Learning (DL) Solutions for Smart City use cases
Deep Learning (DL) Solutions for Smart City use cases
 
AI driven innovation
AI driven innovation AI driven innovation
AI driven innovation
 
How AI is revolutionizing the world
How AI is revolutionizing the worldHow AI is revolutionizing the world
How AI is revolutionizing the world
 
How NLP is revolutionizing marketing and communications
How NLP is revolutionizing marketing and communications How NLP is revolutionizing marketing and communications
How NLP is revolutionizing marketing and communications
 
AI in Smart Cities
AI in Smart Cities AI in Smart Cities
AI in Smart Cities
 
SF ACM Bay chapter meetup on NLP will revolutionize the world
SF ACM Bay chapter meetup on NLP will revolutionize the world SF ACM Bay chapter meetup on NLP will revolutionize the world
SF ACM Bay chapter meetup on NLP will revolutionize the world
 
The Magic of Image processing using Neural Networks
The Magic of Image processing using Neural Networks The Magic of Image processing using Neural Networks
The Magic of Image processing using Neural Networks
 
The Magic of Text Summarization using Deep Networks
The Magic of Text Summarization using Deep NetworksThe Magic of Text Summarization using Deep Networks
The Magic of Text Summarization using Deep Networks
 
Natural Language Processing Tech workshop
Natural Language Processing Tech workshop Natural Language Processing Tech workshop
Natural Language Processing Tech workshop
 
The magic of machine translation 20 july 2017
The magic of machine translation 20 july 2017The magic of machine translation 20 july 2017
The magic of machine translation 20 july 2017
 
Summarization and Abstraction using deep learning
Summarization and Abstraction using deep learningSummarization and Abstraction using deep learning
Summarization and Abstraction using deep learning
 
Question Answering in NLP on Mahabharata 24 may 2017
Question Answering in NLP on Mahabharata 24 may 2017Question Answering in NLP on Mahabharata 24 may 2017
Question Answering in NLP on Mahabharata 24 may 2017
 

Recently uploaded

IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
Enterprise Knowledge
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
Earley Information Science
 

Recently uploaded (20)

Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 

Making sense from 3D Point Clouds