Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
NIPS2017reading_3Dreconstruction
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
望月紅葉さんと幸せな家庭を築きたい
January 27, 2018
Research
1.5k
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
NIPS2017reading_3Dreconstruction
望月紅葉さんと幸せな家庭を築きたい
January 27, 2018
Transcript
28 slides
̏࣍ݩ෮ݩʹؔͯ͠ Learning a Multi-View Stereo Machine NIPS2017จಡΈձˏΫοΫύου 1 ಛʹදه͕ͳ͍ݶΓɺҎԼͷࢿྉ͔ΒҾ༻ https://arxiv.org/pdf/1708.05375.pdf
Learning a Multi-View Stereo Machine ▸ චऀ • Abhishek Kar,
Christian Häne, Jitendra Malik ʢUC Berkeley) ▸ ֓ཁ • Multi View StereoʢMVSʣʹΑΔີͳ3࣍ݩ෮ݩΛDeep LearningͰEnd2Endʹֶश • MVSΛ”ֶशͰ͖Δ”ͷͰແ͍͔ͱ͍͏ٙʹ͑Δ 2
എܠ ▸ Multi View Stereoͱ 1. ಛநग़ 2. Ϛονϯά 3.
̏࣍ݩ෮ݩ 4. Τϥʔͷআڈ 3
എܠ ▸ Multi View Stereoͱ 1. ಛநग़ 2. Ϛονϯά 3.
̏࣍ݩ෮ݩ 4. Τϥʔͷআڈ ==> DeepԿͰશͯղܾͰ͖ͦ͏ 4
എܠ ▸ Multi View Stereoͱ 1. ಛநग़ɹ← CNNͰ͍͚Δ 2. Ϛονϯά
3. ̏࣍ݩ෮ݩ 4. Τϥʔͷআڈ 5
എܠ ▸ Multi View Stereoͱ 1. ಛநग़ 2. Ϛονϯάɹ← CNNͱRNNͰ͍͚Δ
3. ̏࣍ݩ෮ݩ 4. Τϥʔͷআڈ 6
എܠ ▸ Multi View Stereoͱ 1. ಛநग़ 2. Ϛονϯά 3.
̏࣍ݩ෮ݩɹ← DeconvͰ͍͚Δ 4. Τϥʔͷআڈ 7
എܠ ▸ Multi View Stereoͱ 1. ಛநग़ 2. Ϛονϯά 3.
̏࣍ݩ෮ݩ 4. Τϥʔͷআڈɹ← Encoder-DecoderͰ͍͚Δ 8
DeepԿͰࡾ࣍ݩ෮ݩ ▸ 3DR2N2(ECCV2016) • ෳը૾ΛΤϯίʔυ͠ɺLSTMͰϚονϯά 9 http://3d-r2n2.stanford.edu
DeepԿͰࡾ࣍ݩ෮ݩ ▸ 3D Shape Reconstruction by Modeling 2.5D Sketch (NIPS2017)
• ϦΞϧͷը૾͔Β2.5DͷεέονΛى͜͠ɺ2.5DεέονΛͱʹ 3DshapeਪఆΛEnd2EndֶशͰ͢Δ 10 https://arxiv.org/pdf/1711.03129.pdf
͢༰ ▸ શମ૾ ▸ ख๏ ▸ ࣮ݧ ▸ ·ͱΊ 11
શମ૾ 12 http://bair.berkeley.edu/blog/2017/09/05/unified-3d/
શମ૾ 13 Learnt Stereo Machines
ख๏ ▸ Image Encoder • Encoder-DecoderܕʢU-netʣͷઃܭ • Ϛονϯάʹ༻͍Δ̎DͷಛϚοϓ࡞ • ࣍ݩ2DnಛϚο
14
ख๏ ▸ Unplojection ▸ 2࣍ݩͷಛϚοϓ3࣍ݩͷຊདྷ͋Δ͖ಛϚοϓ͔ΒࣹӨ ▸ 3࣍ݩάϦουʹٯࣹӨ 15 http://bair.berkeley.edu/blog/2017/09/05/unified-3d/
ख๏ ▸ Unplojection ▸ 2࣍ݩͷಛϚοϓ3࣍ݩͷຊདྷ͋Δ͖ಛϚοϓ͔ΒࣹӨ ▸ 3࣍ݩάϦουʹٯࣹӨ 16 http://bair.berkeley.edu/blog/2017/09/05/unified-3d/
ख๏ ▸ Unplohection ▸ 2࣍ݩͷಛϚοϓ3࣍ݩͷຊདྷ͋Δ͖ಛϚοϓ͔ΒࣹӨ ▸ 3࣍ݩάϦουʹٯࣹӨ 17 http://bair.berkeley.edu/blog/2017/09/05/unified-3d/
ख๏ ▸ Unplohection ▸ 2࣍ݩͷಛϚοϓ3࣍ݩͷຊདྷ͋Δ͖ಛϚοϓ͔ΒࣹӨ ▸ 3࣍ݩάϦουʹٯࣹӨ 18 http://bair.berkeley.edu/blog/2017/09/05/unified-3d/
ख๏ ▸ Recurrent Grid Fusion • 3࣍ݩͷಛϚοϓͷϚονϯάΛGated Recurrent Unit(GRU)Ͱ •
GRUʹ͍࣋ͬͯͨ͘Ίɺ3D convolutionΛ༻ • ͜ͷաఔ͕MVSͷܭࢉϚονϯάΛ୲ • ֶशͷࡍը૾ͷೖྗॱΛϥϯμϜʹೖΕସ͑Δ 19
ख๏ ▸ 3D Grid Reasoning • GRUͰ̏࣍ݩάϦουʹͨ͠ΒϊΠζ͕ଟ͔ͬͨɻ • 3U-netͰEncode Decode͢ΔͱFilteringͰ͖Δ
20
ख๏ ▸ Differentiable Projection • Depthͷ෮ݩʹL1 loss(high frequency informationͷͨΊ) •
Voxelͷ෮ݩʹvoxel͝ͱͷcross entropy loss 21
࣮ݧ ▸ σʔληοτ • ShapeNetσʔλΛར༻ • ̏࣍ݩCADϞσϧͷެ։σʔληοτ 22 https://shapenet.cs.stanford.edu/shrec17/
࣮ݧ • ೖྗը૾ ▸ ShapeNetͷ3DϞσϧΛϨϯμϦϯάͯ͠224x224x3 ▸ ̍ࢹ͋ͨΓ̐ຕ ▸ Χϝϥϙʔζ •
Ξτϓοτ ▸ Depth: 224x224x3 ▸ Voxel: 32x32x32 23
࣮ݧ ▸ ݁Ռ 24 3DR2N2ͱൺɺࡉ͔͍෮ݩ͕Մೳ
࣮ݧ ▸ ݁Ռ 25 3DR2N2ͱൺɺগͳ͍ຕͰ෮ݩ͕Մೳ ຕ૿͑Δͱੑೳ্͕͕Δ
࣮ݧ ▸ ݁Ռ 26 stereo matchingͰ෮ݩ͠ͳ͍ ૭෮ݩՄೳ
࣮ݧ ▸ ݁Ռ 27 stereo matchingʹൺ গͳ͍ຕͰ෮ݩ͕Մೳ චऀᐌ͘ CNNͷίϯςΫετΛݟΔྗ ैདྷͷstereo
matchingΛ͙྇ DepthMapͷਪఆ݁ՌΛෳΈ߹Θͤͯ̏࣍ݩ෮ݩͨ͠
·ͱΊ ▸ Learnt Stereo MachinesΛఏҊ ▸ ෳࢹ͔Βͷೖྗը૾Λݩʹɺ DepthMapͱVoxelͷਪఆ͕Մೳͱͳͬͨ ▸ ՝
• ग़ྗVoxel͕32x32x32ͱখ͍͞ 28
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
190
unsupervised-learning-of-depth-and-ego-motion-from-monocular-video-using-3d-geometric-constraints
momijifullmoon
0
510
ABEJA Innovation Meetup NIPS PointNet++
momijifullmoon
1
530
Other Decks in Research
See All in Research
Du suivi individuel à la sélection animale : comment Digi4Live valorise les données des technologies numériques en élevage
institutdelelevage
PRO
0
120
ふとした出会いで生まれたSkillが、 社内利用1位になるまで
mikimhk
22
25k
Physical AIでモデリングはどう変わるか/How Physical AI Will Change Modeling
stktu
0
350
Who’s Behind the Divide?
sirmatrixpage
1
1.6k
データサイエンティストの就労意識~2015 → 2026 一般(個人)会員アンケートより
datascientistsociety
PRO
0
1.2k
VLMの推論を高速化する視覚トークン削減の仕組み
tattaka
2
440
PHTalks Bengaluru - SSRF When All Else Fails
dk999
0
1.2k
Santé et fertilité des sols : ce que nous disent les pratiques dans les systèmes de polyculture-élevage
institutdelelevage
PRO
0
160
Méthane 2030 : Développer des solutions de réduction des émissions de méthane entérique : 1ers résultats
institutdelelevage
PRO
0
120
AI対話に何を挟むか ― 高回転対話・デジタル摘録・手書き記録による創造体験の違い|日本創造学会2026
ishiirikie
0
210
Evaluating LLM Reliability Across Facts, Evidence, and Cultures
yukiar
0
250
量子サマースクール2026「量子計算機アーキテクチャ分野の概観」
youten622
1
1k
Featured
See All Featured
The innovator’s Mindset - Leading Through an Era of Exponential Change - McGill University 2025
jdejongh
PRO
1
400
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
3
980
Evolving SEO for Evolving Search Engines
ryanjones
0
360
ReactJS: Keep Simple. Everything can be a component!
pedronauck
666
130k
A Soul's Torment
seathinner
9
3.9k
How To Stay Up To Date on Web Technology
chriscoyier
790
250k
Docker and Python
trallard
47
4.3k
How People are Using Generative and Agentic AI to Supercharge Their Products, Projects, Services and Value Streams Today
helenjbeal
2
400
Stop Working from a Prison Cell
hatefulcrawdad
274
21k
Are puppies a ranking factor?
jonoalderson
2
4.2k
Navigating Team Friction
lara
192
16k
Redefining SEO in the New Era of Traffic Generation
szymonslowik
1
530