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
750
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
AI for Kids:小学生に画像認識を教えてみた話
peisuke
1
8
LangGraphで始めるマルチエージェントシステム
peisuke
13
4.2k
Self-RAG: Learning to Retrieve, Generate and Critique through Self-Reflections
peisuke
9
1.5k
Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
peisuke
0
10k
LangChain Toolsの運用と改善
peisuke
4
2.6k
TTS Skins: Speaker Conversion via ASR
peisuke
0
390
A Quantum Computational Approach to Correspondence Problems on Point Sets
peisuke
0
690
F0-Consistent Many-to-many Non-parallel Voice Conversion via Conditional Autoencoder
peisuke
0
190
YOLACT real-time instance segmentation
peisuke
1
270
Other Decks in Technology
See All in Technology
AWSアカウントのセキュリティ自動化、どこまで進める? 最適な設計と実践ポイント
yuobayashi
7
570
ESXi で仮想化した ARM 環境で LLM を動作させてみるぞ
unnowataru
0
170
Change Managerを活用して本番環境へのセキュアなGUIアクセスを統制する / Control Secure GUI Access to the Production Environment with Change Manager
yuj1osm
0
100
Share my, our lessons from the road to re:Invent
naospon
0
140
分解して理解する Aspire
nenonaninu
2
1k
【5分でわかる】セーフィー エンジニア向け会社紹介
safie_recruit
0
18k
AWSを活用したIoTにおけるセキュリティ対策のご紹介
kwskyk
0
350
役員・マネージャー・著者・エンジニアそれぞれの立場から見たAWS認定資格
nrinetcom
PRO
3
5.9k
AIエージェント元年@日本生成AIユーザ会
shukob
1
200
OPENLOGI Company Profile
hr01
0
60k
Raycast AI APIを使ってちょっと便利な拡張機能を作ってみた / created-a-handy-extension-using-the-raycast-ai-api
kawamataryo
0
210
MIMEと文字コードの闇
hirachan
2
1.4k
Featured
See All Featured
Six Lessons from altMBA
skipperchong
27
3.6k
Building Your Own Lightsaber
phodgson
104
6.2k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
366
25k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
133
33k
The World Runs on Bad Software
bkeepers
PRO
67
11k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
rmw
33
2.8k
Being A Developer After 40
akosma
89
590k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
27
1.6k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
129
19k
The Art of Programming - Codeland 2020
erikaheidi
53
13k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
175
52k
A Philosophy of Restraint
colly
203
16k
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