Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
ABEJA Innovation Meetup NIPS PointNet++
Search
望月紅葉さんと幸せな家庭を築きたい
January 01, 2018
Programming
1
490
ABEJA Innovation Meetup NIPS PointNet++
望月紅葉さんと幸せな家庭を築きたい
January 01, 2018
Tweet
Share
More Decks by 望月紅葉さんと幸せな家庭を築きたい
See All by 望月紅葉さんと幸せな家庭を築きたい
shadow-detection-with-conditional-generative-adversarial-networks
momijifullmoon
0
140
unsupervised-learning-of-depth-and-ego-motion-from-monocular-video-using-3d-geometric-constraints
momijifullmoon
0
400
NIPS2017reading_3Dreconstruction
momijifullmoon
0
1.5k
Other Decks in Programming
See All in Programming
本当だってば!俺もTRICK 2022に入賞してたんだってば!
jinroq
0
240
Compose Navigation実装の見通しを良くする
hiroaki404
0
180
Develop Faster With FrankenPHP
dunglas
2
2.4k
Denoでフロントエンド開発 2025年春版 / Frontend Development with Deno (Spring 2025)
petamoriken
1
1.3k
ステートソーシング型イベント駆動の視点で捉えるCQRS+ES
shinnosuke0522
1
320
Scala 3 で GLSL のための c-like-for を実装してみた
exoego
1
180
研究開発と実装OSSと プロダクトの好循環 / A virtuous cycle of research and development implementation OSS and products
linyows
1
190
Return of the Full-Stack Developer
simas
PRO
1
310
読もう! Android build ドキュメント
andpad
1
240
ニックトレイン登壇資料
ryotakurokawa
0
140
ミリしらMCP勉強会
watany
1
100
eBPF Updates (March 2025)
kentatada
0
130
Featured
See All Featured
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
7
610
10 Git Anti Patterns You Should be Aware of
lemiorhan
PRO
656
60k
Into the Great Unknown - MozCon
thekraken
36
1.7k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
31
4.7k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
16k
Build your cross-platform service in a week with App Engine
jlugia
229
18k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
280
13k
VelocityConf: Rendering Performance Case Studies
addyosmani
328
24k
Rebuilding a faster, lazier Slack
samanthasiow
80
8.9k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
How STYLIGHT went responsive
nonsquared
99
5.4k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
45
9.5k
Transcript
PointNet++: Deep Hierarchical Feature Learning on Point Sets
in a Metric Space NIPSಡΈձˏABEJA 1
PointNet++ͷ֓ཁ ▸ ஶऀ: Charles R. Qi, Li Yi, Hao Su,
Leonidas J. Guibas ɹɹ ˏελϯϑΥʔυ ▸ ֓ཁ ▸ ܈Λͦͷ··ೖྗ͠ɺͦͷΫϥεྨɺ SegmentationΛߦ͏PointNetͷվྑใࠂ ▸ PointNetͷऑͰ͋ͬͨ܈ີґଘΛࠀɺ ͓Αͼ֊తͳֶशΛͰ͖ΔΑ͏ʹ ʮSampling Layerʯͱ ʮGrouped LayerʯΛఏҊ 2
എܠ ▸ ̏࣍ݩͷधཁ 3 ࣗಈӡస AR ઃܭ
ͷྲྀΕ ▸ എܠ ▸ PointNetʹ͍ͭͯ ▸ ख๏ ▸ ࣮ݧ ▸
·ͱΊ 4
എܠ ▸ ̏࣍ݩͷσʔλ 5 ɹɹ܈ɹɹ ɹɹϝογϡɹɹ Voxel Өɹ RGB-D
എܠ ▸ طଘͷख๏ ▸ ܈Λผͷදݱʹม͍ͯͨ͠ 6 Unstructured, Unordered ͳ܈Λͦͷ··ೖྗ Ͱ͏·͍͘͘Α͏ͳख๏
==> PointNetΛఏҊ@CVPR2017
PointNetͷ͓͞Β͍ ▸ ղ͘λεΫ 7 Classification Segmentation Scene Parsing ೖྗ
PointNetͷ͓͞Β͍ ▸ ઃܭ 8
PointNetͷ͓͞Β͍ ▸ ՝ 9 PointNet֤ʹ͓͍ͯɺlocalͷใ͕ফ͑Δ ֊తಛֶशͰ͖ͳ͍ ෳ֊ͷநԽͰ͖ͳ͍ GlobalͷಛֶशͷΈ ͋Δ͘͠શͯͷ
PointNetͷ͓͞Β͍ ▸ localͷใ͕ফ͑Δͱ 10 globalͷใɺઈର࠲ඪʹґଘͯ͠͠·͏ͷͰɺ segmentationͰະͷͷʹରԠͰ͖ͳ͍
PointNet++Ͱ ▸ ֊తֶश ▸ localͳใΛ͢ 11 ▸ ܈ີʹϩόετʹ
ΞʔΩςΫνϟ 12
֊తͳֶश 13
֊తͳֶश ▸ Sampling layer ▸ Farthest Point Sampling (FPS) 14
https://www.groundai.com/project/parametric-manifold-learning-via-sparse-multidimensional-scaling/
▸ Grouping layer ▸ radius based ball query ֊తͳֶश 15
PointNet layer Convolution layer Input Δԋࢉ ԋࢉͰݟΔ ൣғ Radius ball query ɹ܈ɹ PointNetʢॱ൪ීวʣ ߦྻʢݻఆͷϐΫηϧʣ ΈࠐΈʢॱ൪ґଘʣ ɹີͳߦྻɹ
֊తͳֶश ▸ PointNet layer 16 N1ݸͷʹର͠ C1ݸͷಛ࡞ ॏΈshare
֊తͳֶश ▸ PointNet layer 17 x1,y1,z1,ΫΤϦ1,ಛ1 x2,y2,z2,ΫΤϦ2,ಛ2 x3,y3,z3,ΫΤϦ3,ಛ3 xN1,yN1,zN1,ΫΤϦN1ಛN1 MLP
MLP MLP MLP x1,y1,z1,ಛ1 x2,y2,z2,ಛ2 x3,y3,z3,ಛ3 xN1,yN1,zN1,ಛN1 ॏΈShare
ີґଘࠀख๏ ▸ ̏࣍ݩͷଌఆͰ܈ີ͕Ұൠతͳ՝ 18 ==> ܈ີʹϩόετʹ͍ͨ͠
ີґଘࠀख๏ ▸ SamplingͱGroupingΛෳ༻ҙ 19 MRGͷํ͕࣍ͰपลͱͷಛΛर͑Δ
Classification ࣮ݧ 20
▸ ModelNet40ʹରͯ͠ Classification ࣮ݧ 21 PointNetʹൺɺPointNet++ྨਫ਼্ CNNϕʔεͷख๏ʹউར
ີґଘ࣮ݧ 22 ಛʹ܈͕গͳ͍ͱɺMRG͕༗ޮ
Segmentation ࣮ݧ 23 ૠɿɹIDW (ٯڑՃॏ) Unitpointnet: ֤ͰMLP
Segmentation ࣮ݧ ▸ ݁Ռ 24 MSGΛೖΕΔ͜ͱͰɺෆۉҰͳ܈Ͱ͏·͍͘͘
Segmentation ࣮ݧ ▸ ݁Ռ 25 PointNetΑΓՈ۩ͷsegmentation্͕ख͍͘͘
ඇϢʔΫϦου ڑۭؒͰͷ࣮ݧ 26 WKS , HKS, multi-scale Gaussian curvature
Feature Visualization ▸ ࠷ॳͷͷॏΈΛՄࢹԽ 27 ฏ໘ɺίʔφʔͱ͔Λֶश
·ͱΊ ▸ PointNetΛ֦ுͨ͠ख๏PointNet++Λൃද ▸ CVPR2017=>NIPS2017ʹ̍ຊ௨͍ͯ͠Δɻɻɻ ▸ Sampling layerɺGrouped layerΛऔΓೖΕ֊తͳֶश ▸
MRGɺMSGΛఏҊ͠ɺ܈ີʹґଘ͠ͳֶ͍श ▸ ̏࣍ݩ܈ͷσʔληοτʹରͯ͠ɺSoTAୡ ▸ ݱʹߦͬͨײ ▸ ஶऀͱ͢͜ͱͰࡉ͔ͳใΛर͑Δ 28