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
800
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
VGGT: Visual Geometry Grounded Transformer
peisuke
1
1.2k
AI for Kids:小学生に画像認識を教えてみた話
peisuke
1
52
LangGraphで始めるマルチエージェントシステム
peisuke
14
4.7k
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
420
A Quantum Computational Approach to Correspondence Problems on Point Sets
peisuke
0
750
F0-Consistent Many-to-many Non-parallel Voice Conversion via Conditional Autoencoder
peisuke
0
230
Other Decks in Technology
See All in Technology
Behind Postgres 18: The People, the Code, & the Invisible Work | Claire Giordano | PGConfEU 2025
clairegiordano
0
140
マルチエージェントのチームビルディング_2025-10-25
shinoyamada
0
180
NLPコロキウム20251022_超効率化への挑戦: LLM 1bit量子化のロードマップ
yumaichikawa
3
500
QA業務を変える(!?)AIを併用した不具合分析の実践
ma2ri
0
150
dbtとAIエージェントを組み合わせて見えたデータ調査の新しい形
10xinc
1
450
オブザーバビリティと育てた ID管理・認証認可基盤の歩み / The Journey of an ID Management, Authentication, and Authorization Platform Nurtured with Observability
kaminashi
1
720
AIとともに歩んでいくデザイナーの役割の変化
lycorptech_jp
PRO
0
880
ゼロコード計装導入後のカスタム計装でさらに可観測性を高めよう
sansantech
PRO
1
460
オブザーバビリティが育むシステム理解と好奇心
maruloop
2
1.3k
OSSで50の競合と戦うためにやったこと
yamadashy
3
990
ラスベガスの歩き方 2025年版(re:Invent 事前勉強会)
junjikoide
0
180
Dylib Hijacking on macOS: Dead or Alive?
patrickwardle
0
480
Featured
See All Featured
BBQ
matthewcrist
89
9.9k
Typedesign – Prime Four
hannesfritz
42
2.8k
YesSQL, Process and Tooling at Scale
rocio
173
15k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
253
22k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
333
22k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
32
1.7k
Balancing Empowerment & Direction
lara
5
700
Six Lessons from altMBA
skipperchong
29
4k
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
12
1.2k
Build your cross-platform service in a week with App Engine
jlugia
233
18k
Designing for Performance
lara
610
69k
Git: the NoSQL Database
bkeepers
PRO
431
66k
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