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
1.5k
AI for Kids:小学生に画像認識を教えてみた話
peisuke
1
78
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
善意の活動は、なぜ続かなくなるのか ーふりかえりが"構造を変える判断"になった半年間ー
matsukurou
0
590
かわいい身体と声を持つ そういうものに私はなりたい
yoshimura_datam
0
150
Sansan Engineering Unit 紹介資料
sansan33
PRO
1
3.7k
会社紹介資料 / Sansan Company Profile
sansan33
PRO
13
400k
プロンプトエンジニアリングを超えて:自由と統制のあいだでつくる Platform × Context Engineering
yuriemori
0
480
手軽に作れる電卓を作って イベントソーシングに親しもう CQRS+ESカンファレンス2026
akinoriakatsuka
0
460
Models vs Bounded Contexts for Domain Modularizati...
ewolff
0
210
持続可能な開発のためのミニマリズム
sansantech
PRO
3
230
RALGO : AIを組織に組み込む方法 -アルゴリズム中心組織設計- #RSGT2026 / RALGO: How to Integrate AI into an Organization – Algorithm-Centric Organizational Design
kyonmm
PRO
3
1.5k
「違う現場で格闘する二人」——社内コミュニティがつないだトヨタ流アジャイルの実践とその先
shinichitakeuchi
0
480
みんなでAI上手ピーポーになろう! / Let’s All Get AI-Savvy!
kaminashi
0
150
Bill One 開発エンジニア 紹介資料
sansan33
PRO
4
17k
Featured
See All Featured
Design in an AI World
tapps
0
130
Conquering PDFs: document understanding beyond plain text
inesmontani
PRO
4
2.2k
What's in a price? How to price your products and services
michaelherold
246
13k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
49
3.3k
Unlocking the hidden potential of vector embeddings in international SEO
frankvandijk
0
150
How STYLIGHT went responsive
nonsquared
100
6k
sira's awesome portfolio website redesign presentation
elsirapls
0
120
Digital Ethics as a Driver of Design Innovation
axbom
PRO
0
140
The agentic SEO stack - context over prompts
schlessera
0
590
Site-Speed That Sticks
csswizardry
13
1k
Making Projects Easy
brettharned
120
6.5k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
48
9.8k
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