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
730
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
LangGraphで始めるマルチエージェントシステム
peisuke
13
4k
AutoGenで作るLLM Agen
peisuke
1
1.4k
Self-RAG: Learning to Retrieve, Generate and Critique through Self-Reflections
peisuke
9
1.4k
Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
peisuke
0
9.4k
LangChain Toolsの運用と改善
peisuke
4
2.6k
TTS Skins: Speaker Conversion via ASR
peisuke
0
370
A Quantum Computational Approach to Correspondence Problems on Point Sets
peisuke
0
670
F0-Consistent Many-to-many Non-parallel Voice Conversion via Conditional Autoencoder
peisuke
0
180
YOLACT real-time instance segmentation
peisuke
1
260
Other Decks in Technology
See All in Technology
大幅アップデートされたRagas v0.2をキャッチアップ
os1ma
2
530
C++26 エラー性動作
faithandbrave
2
730
組織に自動テストを書く文化を根付かせる戦略(2024冬版) / Building Automated Test Culture 2024 Winter Edition
twada
PRO
13
3.7k
TSKaigi 2024 の登壇から広がったコミュニティ活動について
tsukuha
0
160
私なりのAIのご紹介 [2024年版]
qt_luigi
1
120
Qiita埋め込み用スライド
naoki_0531
0
4.7k
UI State設計とテスト方針
rmakiyama
2
510
5分でわかるDuckDB
chanyou0311
10
3.2k
Amazon Kendra GenAI Index 登場でどう変わる? 評価から学ぶ最適なRAG構成
naoki_0531
0
110
ずっと昔に Star をつけたはずの思い出せない GitHub リポジトリを見つけたい!
rokuosan
0
150
NW-JAWS #14 re:Invent 2024(予選落ち含)で 発表された推しアップデートについて
nagisa53
0
260
Oracle Cloudの生成AIサービスって実際どこまで使えるの? エンジニア目線で試してみた
minorun365
PRO
4
280
Featured
See All Featured
GraphQLの誤解/rethinking-graphql
sonatard
67
10k
How to train your dragon (web standard)
notwaldorf
88
5.7k
It's Worth the Effort
3n
183
28k
Why You Should Never Use an ORM
jnunemaker
PRO
54
9.1k
Scaling GitHub
holman
458
140k
Rails Girls Zürich Keynote
gr2m
94
13k
GitHub's CSS Performance
jonrohan
1030
460k
Build your cross-platform service in a week with App Engine
jlugia
229
18k
Building a Modern Day E-commerce SEO Strategy
aleyda
38
7k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
191
16k
GraphQLとの向き合い方2022年版
quramy
44
13k
Unsuck your backbone
ammeep
669
57k
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