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
88
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
430
A Quantum Computational Approach to Correspondence Problems on Point Sets
peisuke
0
780
Other Decks in Technology
See All in Technology
内製AIチャットボットで学んだDatadog LLM Observability活用術
mkdev10
0
120
Claude Code のコード品質がばらつくので AI に品質保証させる仕組みを作った話 / A story about building a mechanism to have AI ensure quality, because the code quality from Claude Code was inconsistent
nrslib
13
8.4k
VPCエンドポイント意外とお金かかるなぁ。せや、共有したろ!
tommy0124
1
630
AI時代の「本当の」ハイブリッドクラウド — エージェントが実現した、あの頃の夢
ebibibi
0
130
"作る"から"使われる"へ:Backstage 活用の現在地
sbtechnight
0
150
僕、S3 シンプルって名前だけど全然シンプルじゃありません よろしくお願いします
yama3133
1
220
AI駆動AI普及活動 ~ 社内AI活用の「何から始めれば?」をAIで突破する
oracle4engineer
PRO
1
110
JAWS DAYS 2026 ExaWizards_20260307
exawizards
0
440
詳解 強化学習 / In-depth Guide to Reinforcement Learning
prinlab
0
110
CyberAgentの生成AI戦略 〜変わるものと変わらないもの〜
katayan
0
240
Zeal of the Convert: Taming Shai-Hulud with AI
ramimac
0
120
VLAモデル構築のための AIロボット向け模倣学習キット
kmatsuiugo
0
180
Featured
See All Featured
Unlocking the hidden potential of vector embeddings in international SEO
frankvandijk
0
200
Conquering PDFs: document understanding beyond plain text
inesmontani
PRO
4
2.5k
30 Presentation Tips
portentint
PRO
1
250
Music & Morning Musume
bryan
47
7.1k
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
Tell your own story through comics
letsgokoyo
1
840
Building AI with AI
inesmontani
PRO
1
800
Large-scale JavaScript Application Architecture
addyosmani
515
110k
Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation
inesmontani
PRO
3
2.1k
Bridging the Design Gap: How Collaborative Modelling removes blockers to flow between stakeholders and teams @FastFlow conf
baasie
0
480
Speed Design
sergeychernyshev
33
1.6k
The Illustrated Guide to Node.js - THAT Conference 2024
reverentgeek
1
310
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