Real-Time Hair Filtering with Convolutional Neural Networks

被引：0

作者：

Currius, Roc R. ^{[1
]}

Assarsson, Ulf ^{[1
]}

Sintorn, Erik ^{[1
]}

机构：

[1] Chalmers Inst Technol, Gothenburg, Sweden

来源：

PROCEEDINGS OF THE ACM ON COMPUTER GRAPHICS AND INTERACTIVE TECHNIQUES | 2022年 / 5卷 / 01期

基金：

瑞典研究理事会;

关键词：

hair; real-time; transparency; filtering; neural networks;

D O I：

10.1145/3522606

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

Rendering of realistic-looking hair is in general still too costly to do in real-time applications, from simulating the physics to rendering the fine details required for it to look natural, including self-shadowing. We show how an autoencoder network, that can be evaluated in real time, can be trained to filter an image of few stochastic samples, including self-shadowing, to produce a much more detailed image that takes into account real hair thickness and transparency.

引用

页数：15

共 50 条

[41] Robust Real-Time Detection of Laparoscopic Instruments in Robot Surgery Using Convolutional Neural Networks with Motion Vector Prediction
Jo, Kyungmin
Choi, Yuna
Choi, Jaesoon
Chung, Jong Woo
APPLIED SCIENCES-BASEL, 2019, 9 (14):
[42] Real-Time Fuzzy Digital Filtering
Garcia Infante, Juan Carlos
Medel Juarez, Jose de Jesus
Guevara Lopez, Pedro
COMPUTACION Y SISTEMAS, 2008, 11 (04): : 390 - 401
[43] Real-time neural networks application of micro-electroforming for different geometry forms
Shiah, Sheau-Wen
Chang, Pai-Yu
Heh, Tzeng-Yuan
Lin, Po-Hung
AGENT AND MULTI-AGENT SYSTEMS: TECHNOLOGIES AND APPLICATIONS, PROCEEDINGS, 2008, 4953 : 21 - +
[44] Real-Time Pupil-Tracking Embedded-System based on Neural Networks
Emanuel Ordonez, Cristian
Blotta, Eduardo
Pastore, Juan I.
Dai Pra, Lucia
Isabel Passoni, Lucia
2017 XVII WORKSHOP ON INFORMATION PROCESSING AND CONTROL (RPIC), 2017,
[45] Real-Time Continuous Pose Recovery of Human Hands Using Convolutional Networks
Tompson, Jonathan
Stein, Murphy
Lecun, Yann
Perlin, Ken
ACM TRANSACTIONS ON GRAPHICS, 2014, 33 (05):
[46] Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks
Abdeljaber, Osama
Avci, Onur
Kiranyaz, Serkan
Gabbouj, Moncef
Inman, Daniel J.
JOURNAL OF SOUND AND VIBRATION, 2017, 388 : 154 - 170
[47] Real-time detection of peak cardiac motion signal using one-dimensional dilated convolutional neural networks
Wu, Tongtong
PROCEEDINGS OF 2023 7TH INTERNATIONAL CONFERENCE ON ELECTRONIC INFORMATION TECHNOLOGY AND COMPUTER ENGINEERING, EITCE 2023, 2023, : 749 - 753
[48] A Real-Time American Sign Language Recognition System using Convolutional Neural Network for Real Datasets
Kadhim, Rasha Amer
Khamees, Muntadher
TEM JOURNAL-TECHNOLOGY EDUCATION MANAGEMENT INFORMATICS, 2020, 9 (03): : 937 - 943
[49] Neural networks for SISD real time control
Miroslav, C
Stefan, K
INTELLIGENT TECHNOLOGIES - THEORY AND APPLICATIONS: NEW TRENDS IN INTELLIGENT TECHNOLOGIES, 2002, 76 : 321 - 328
[50] Neural networks for real-time estimation of parameters of signals in power systems
Cichocki, A
Kostyla, P
Lobos, T
Waclawek, Z
ENGINEERING INTELLIGENT SYSTEMS FOR ELECTRICAL ENGINEERING AND COMMUNICATIONS, 1998, 6 (03): : 131 - 140

← 1 2 3 4 5 →