Material Recognition for Immersive Interactions in Virtual/Augmented Reality

被引：0

作者：

Heng, Yuwen ^{[1
]}

Dasmahapatra, Srinandan ^{[1
]}

Kim, Hansung ^{[1
]}

机构：

[1] Univ Southampton, Sch Elect & Comp Sci, Southampton, Hants, England

来源：

2023 IEEE CONFERENCE ON VIRTUAL REALITY AND 3D USER INTERFACES ABSTRACTS AND WORKSHOPS, VRW | 2023年

基金：

英国工程与自然科学研究理事会;

关键词：

Human-centered computing-Human computer interaction (HCI)-Interaction paradigms-Virtual reality; Computing methodologies-Artificial intelligence-Computer vision-Scene understanding;

D O I：

10.1109/VRW58643.2023.00131

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

To provide an immersive experience in a mirrored virtual world such as spatially synchronised audio, visualisation of reproduced real-world scenes and haptic sensing, it is necessary to know the materials of the object surface which provides the optical and acoustic properties for the rendering engine. We focus on identifying materials from real-world images to reproduce more realistic and plausible virtual environments. To cope with considerable variation in material, we propose the DPT architecture which dynamically decides the dependency on different patch resolutions. We evaluate the benefits of learning from multiple patch resolutions on LMD and OpenSurfaces datasets.

引用

页码：577 / 578

页数：2

共 6 条

[1] Alawadh M, 2022, EUR SIGNAL PR CONF, P857
[2] Heng Y., 2022, INT C COMPUTER VISIO
[3] Heng Y., 2022, 33 BRIT MACHINE VISI
[4] Kim H, 2019, 2019 26TH IEEE CONFERENCE ON VIRTUAL REALITY AND 3D USER INTERFACES (VR), P120, DOI 10.1109/VR.2019.8798247
[5] The Mirror World: Preparing for Mixed-Reality Living
Ricci, Alessandro
Piunti, Michele
Tummolini, Luca
Castelfranchi, Cristiano
[J]. IEEE PERVASIVE COMPUTING, 2015, 14 (02) : 60 - 63
[6] Zhang ZL, 2018, 25TH 2018 IEEE CONFERENCE ON VIRTUAL REALITY AND 3D USER INTERFACES (VR), P735, DOI 10.1109/VR.2018.8446260

← 1 →