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
830
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
230
VGGT: Visual Geometry Grounded Transformer
peisuke
1
1.6k
AI for Kids:小学生に画像認識を教えてみた話
peisuke
1
90
LangGraphで始めるマルチエージェントシステム
peisuke
14
4.9k
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
440
A Quantum Computational Approach to Correspondence Problems on Point Sets
peisuke
0
780
Other Decks in Technology
See All in Technology
スピンアウト講座05_実践活用事例
overflowinc
0
1.2k
A4)シラバスを超えて語る、テストマネジメント
moritamasami
0
130
韓非子に学ぶAI活用術
tomfook
2
610
スケールアップ企業でQA組織が機能し続けるための組織設計と仕組み〜ボトムアップとトップダウンを両輪としたアプローチ〜
qa
0
280
モジュラモノリス導入から4年間の総括:アーキテクチャと組織の相互作用について / Architecture and Organizational Interaction
nazonohito51
6
3k
Copilot 宇宙へ 〜生成AIで「専門データの壁」を壊す方法〜
nakasho
0
190
脳が溶けた話 / Melted Brain
keisuke69
1
1k
Why we keep our community?
kawaguti
PRO
0
220
新規事業×QAの挑戦:不確実性を乗りこなす!フェーズごとに求められるQAの役割変革
hacomono
PRO
0
180
20260320_JaSST26_Tokyo_登壇資料.pdf
mura_shin
0
120
事例から紐解くSHIFT流QA支援 ~大規模プロジェクトの品質管理支援、QA組織立ち上げ~ / 20260320 Nozomu Koketsu
shift_evolve
PRO
0
140
Physical AI on AWS リファレンスアーキテクチャ / Physical AI on AWS Reference Architecture
aws_shota
1
130
Featured
See All Featured
From Legacy to Launchpad: Building Startup-Ready Communities
dugsong
0
180
Balancing Empowerment & Direction
lara
5
960
Navigating the Design Leadership Dip - Product Design Week Design Leaders+ Conference 2024
apolaine
0
240
Building an army of robots
kneath
306
46k
How to Think Like a Performance Engineer
csswizardry
28
2.5k
Mozcon NYC 2025: Stop Losing SEO Traffic
samtorres
0
180
SEOcharity - Dark patterns in SEO and UX: How to avoid them and build a more ethical web
sarafernandez
0
150
Art, The Web, and Tiny UX
lynnandtonic
304
21k
Everyday Curiosity
cassininazir
0
180
Designing for Timeless Needs
cassininazir
0
170
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
How GitHub (no longer) Works
holman
316
150k
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