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
GNeRF: GAN-based Neural Radiance Field without ...
Search
peisuke
December 12, 2021
Technology
1
820
GNeRF: GAN-based Neural Radiance Field without Posed Camera
第9回全日本コンピュータビジョン勉強会
ICCV2021論文読み回発表資料
GNeRF: GAN-based Neural Radiance Field without Posed Camera
peisuke
December 12, 2021
Tweet
Share
More Decks by peisuke
See All by peisuke
Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos
peisuke
0
190
VGGT: Visual Geometry Grounded Transformer
peisuke
1
1.4k
AI for Kids:小学生に画像認識を教えてみた話
peisuke
1
74
LangGraphで始めるマルチエージェントシステム
peisuke
14
4.8k
Self-RAG: Learning to Retrieve, Generate and Critique through Self-Reflections
peisuke
9
1.6k
Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
peisuke
0
13k
LangChain Toolsの運用と改善
peisuke
5
2.9k
TTS Skins: Speaker Conversion via ASR
peisuke
0
430
A Quantum Computational Approach to Correspondence Problems on Point Sets
peisuke
0
770
Other Decks in Technology
See All in Technology
AIエージェントを5分で一気におさらい!AIエージェント「構築」元年に備えよう
yakumo
1
120
モダンデータスタックの理想と現実の間で~1.3億人Vポイントデータ基盤の現在地とこれから~
taromatsui_cccmkhd
2
280
Kiro を用いたペアプロのススメ
taikis
4
2k
AWS re:Invent 2025~初参加の成果と学び~
kubomasataka
1
200
20251219 OpenIDファウンデーション・ジャパン紹介 / OpenID Foundation Japan Intro
oidfj
0
550
ESXi のAIOps だ!2025冬
unnowataru
0
410
ハッカソンから社内プロダクトへ AIエージェント ko☆shi 開発で学んだ4つの重要要素
leveragestech
0
330
アラフォーおじさん、はじめてre:Inventに行く / A 40-Something Guy’s First re:Invent Adventure
kaminashi
0
180
Oracle Database@AWS:サービス概要のご紹介
oracle4engineer
PRO
2
440
AWSに革命を起こすかもしれない新サービス・アップデートについてのお話
yama3133
0
520
業務の煩悩を祓うAI活用術108選 / AI 108 Usages
smartbank
9
16k
AI駆動開発ライフサイクル(AI-DLC)の始め方
ryansbcho79
0
230
Featured
See All Featured
AI Search: Where Are We & What Can We Do About It?
aleyda
0
6.8k
Keith and Marios Guide to Fast Websites
keithpitt
413
23k
Rails Girls Zürich Keynote
gr2m
95
14k
Automating Front-end Workflow
addyosmani
1371
200k
Future Trends and Review - Lecture 12 - Web Technologies (1019888BNR)
signer
PRO
0
3.1k
Introduction to Domain-Driven Design and Collaborative software design
baasie
1
520
brightonSEO & MeasureFest 2025 - Christian Goodrich - Winning strategies for Black Friday CRO & PPC
cargoodrich
2
68
Optimising Largest Contentful Paint
csswizardry
37
3.5k
Technical Leadership for Architectural Decision Making
baasie
0
190
Effective software design: The role of men in debugging patriarchy in IT @ Voxxed Days AMS
baasie
0
180
Stewardship and Sustainability of Urban and Community Forests
pwiseman
0
78
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
31
3k
Transcript
GNeRF: GAN-based Neural Radiance Field without Posed Camera @peisuke 9
ABEJA Twitter @peisuke Github https://github.com/peisuke Qiita https://qiita.com/peisuke SlideShare https://www.slideshare.net/FujimotoKeisuke
• • GNeRF: GAN-based Neural Radiance Field without Posed Camera
• • NeRF • • • GAN Radiance Field • RF
NeRF • / 5 •
• • (x,y,z)T (φ1,θ1)T (φ2,θ2)T (x,y,z) φ2,θ2 (x,y,z) φ1,θ1
NeRF • • •
NeRF • NeRF in the Wild • NeRF • iNeRF
• iNeRF NeRF in the Wild BP
条件 iNeRF NeRF-- IDR GNeRF(提案⼿法) 事前学習 必要 不要 不要 不要
粗いカメラ座標 必要 必要 必要 不要 前⽅のみの制約 不要 必要 不要 不要 マスク 不要 不要 必要 不要 • •
• • • • • GAN Radiance Field • RF
• Phase A Phase B
RF • D E 3
GAN Real • • Discriminator Real • Dynamic Patch Sampling
/ 16x16 • Dynamic Patch Sampling
GAN Fake • • NeRF 16x16 • G
• 6 𝑹 = 𝑟!! 𝑟!" 𝑟!# 𝑟"! 𝑟"" 𝑟"#
𝑟#! 𝑟#" 𝑟## 𝒓 = 𝑟!! 𝑟!" 𝑟!# 𝑟"! 𝑟"" 𝑟"# $ • SO(3) NN • On the Continuity of Rotation Representations in Neural Networks
• Inversion network • Static Patch Sampling • E •
Static Patch Sampling
G G D G
• • Inversion network • refinement
• Refinement
• • • • • Photometric loss
• • Generator • NeRF • Discriminator • Instance Normalization
Spectral Normalization • Inversion network • Vision Transformer • • A • A B 1 iteration • B
• • COLMAP NeRF C+n • Refine C+r • Ground
Truth NeRF G+n • • Synthetic-NeRF image size: 400x400 DTU 500x400 • 100 • • Peak Signal-to-Noise Ratio SSIM LPIPS • / • Single TAITAN GPU 30
COLMAP •
• COLMAP Drums
難しいシーン 特徴の少ない シーン
IDR • 3D IDR • IDR • PNSR •
• COLMAP • Drums Lego COLMAP
Ablation Study • • GAN InvNet. PhaseB • • A
B A ABABABAB B
• • • COLMAP • •
• NeRF • • GAN RF • RF • •
• COLMAP