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
SIGGRAPH 2021: Denoising and Guiding
Search
Sponsored
·
SiteGround - Reliable hosting with speed, security, and support you can count on.
→
Tatsuya Yatagawa
September 12, 2021
Technology
120
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
SIGGRAPH 2021: Denoising and Guiding
SIGGRAPH 2021勉強会で使ったスライドです。
https://siggraph.xyz/s2021/
Tatsuya Yatagawa
September 12, 2021
More Decks by Tatsuya Yatagawa
See All by Tatsuya Yatagawa
Event-based Camera Simulation using Monte Carlo Path Tracing with Adaptive Denoising (ICIP 2023)
tatsy
0
570
VC'23 チュートリアル講演 『三次元メッシュと深層学習』
tatsy
0
230
SIGGRAPH 2022: Neural Geometry Processing
tatsy
0
250
Real-time Shading with Free-form Planar Area Lights using Linearly Transformed Cosines (JCGT & I3D 2022)
tatsy
0
1k
SIGGRAPH Asia 2021: Real-Time Rendering
tatsy
0
150
SIGGRAPH 2021: Shape Generation
tatsy
0
200
SIGGRAPH 2021: Meshing
tatsy
0
130
12. Keyboard & Mouse
tatsy
0
230
13. Object selection
tatsy
0
170
Other Decks in Technology
See All in Technology
Agent Skills設計で柔軟性と硬さのバランスが難しい話
nassy20
0
140
OTel × Datadog で 「AI活用」を計測し、改善に繋げる
shihochan
1
420
ぼっちではじめた登壇が「51名」「241件」の発信に化けた
subroh0508
1
240
AWS Security Hub CSPMの成功・失敗体験
cmusudakeisuke
0
260
失敗を資産に変えるClaude Code
shinyasaita
0
720
白金鉱業Meetup_Vol.24_「AIエージェントは分けるほど良い」は本当か? / Is it true that “the more you divide AI agents, the better”?
brainpadpr
1
410
あなたの知らないPDFのアクセシビリティ
lycorptech_jp
PRO
0
220
2026TECHFRESH畢業分享會 - Lightning Talk - E起 See See : 電商推薦讀心術? 數據說了算
line_developers_tw
PRO
0
1.3k
PostgreSQL 19 新機能概要 OSC Hokkaido 2026
nori_shinoda
0
140
人材育成分科会.pdf
_awache
4
300
【Cyber-sec+】経営層を"動かす"ための考え方
hssh2_bin
0
200
Flow 不死:AI 時代 DevOps 的不變本質
cheng_wei_chen
2
330
Featured
See All Featured
Breaking role norms: Why Content Design is so much more than writing copy - Taylor Woolridge
uxyall
0
320
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
133
19k
Raft: Consensus for Rubyists
vanstee
141
7.5k
Hiding What from Whom? A Critical Review of the History of Programming languages for Music
tomoyanonymous
2
860
16th Malabo Montpellier Forum Presentation
akademiya2063
PRO
0
150
Information Architects: The Missing Link in Design Systems
soysaucechin
0
970
The SEO Collaboration Effect
kristinabergwall1
1
490
Collaborative Software Design: How to facilitate domain modelling decisions
baasie
1
250
AI Search: Implications for SEO and How to Move Forward - #ShenzhenSEOConference
aleyda
1
1.3k
Visual Storytelling: How to be a Superhuman Communicator
reverentgeek
2
560
Bootstrapping a Software Product
garrettdimon
PRO
307
120k
Into the Great Unknown - MozCon
thekraken
41
2.6k
Transcript
None
⚫ ⚫ ⚫ ⚫ 前半2つがNNによるレンダリング法の発展, 後半2つがデノイズに関する研究. 全ての研究がニューラルネットを利用している
None
None
None
None
⚫ ⚫
None
None
⚫ ⚫
None
⚫ ⚫
⚫ ⚫
⚫ ⚫
⚫ ⚫
⚫ ⚫
⚫ ⚫ ⚫ ⚫
⚫ 𝑦1 , 𝑦2 ⚫ 𝑦3 , 𝑦4
重みパラメータ ഥ 𝐖𝐭 を慣性𝛈𝐭 を使って徐々に更新 𝛼 = 0 𝛼 =
0.9 𝛼 = 0.99
None
None
None
None
⚫ ⚫
⚫ ⚫
None
None
None
⚫ ⚫ ⚫
None
𝑘
None
⚫ ⚫
⚫ ⚫ ⚫ ⚫ 2番目のNCV以外は比較的素直な従来法の発展といった印象. NRC (+ReSTIR)はNVIDIAらしく実用よりの研究に仕上がっている.