A LIGHTWEIGHT HYBRID REPRESENTATION FOR VIRTUAL COMPLEX SCENES

被引:0
|
作者
Shao, Shuai [1 ]
Jin, Xin [1 ]
机构
[1] Tsinghua Univ, Shenzhen Int Grad Sch, Shenzhen 518055, Peoples R China
关键词
Lightweight representation; shape modeling; hybrid rendering; real-time rendering; deep learning; FIELDS;
D O I
10.1109/ICIP49359.2023.10222844
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
While virtual scenes with complex geometries and high-resolution physically based rendering(PBR) material textures are capable of representing details, they often occupy a large amount of memory and require significant manual editing by artists. In this paper, we introduce a new framework for representing virtual scenes more efficiently. Our framework utilizes a lightweight hybrid representation that combines traditional polygon-based meshes and material textures with learned neural textures. By using simplified geometries and lower-resolution PBR material textures, our representation achieves a compact size while maintaining the freedom for user-friendly scene editing of materials and illuminations. Additionally, we have designed a hybrid rendering pipeline to render the lightweight representation with ray-traced visual quality at real-time frame rates. Our approach reduces memory requirements, eliminates the need for manual editing, and is easy to train. We demonstrate the effectiveness of our framework on a variety of virtual complex scenes.
引用
收藏
页码:2875 / 2879
页数:5
相关论文
共 50 条
  • [21] DISTRIBUTED SUPERCOMPUTING TO ACHIEVE REAL-TIME REPRESENTATION AND MANIPULATION OF COMPLEX SCENES
    ENCARNACAO, J
    KOBERLE, G
    NING, Z
    COMPUTERS IN INDUSTRY, 1990, 14 (1-3) : 23 - 33
  • [22] Superquadrics-based object representation of complex scenes from range images
    Zhang, Y
    Price, JR
    Abidi, MA
    THREE-DIMENSIONAL IMAGE CAPTURE AND APPLICATIONS IV, 2001, 4298 : 56 - 67
  • [23] Lightweight pedestrian detection for multiple scenes
    Zhang Y.
    Li W.
    Guo W.
    Song Z.
    Guangxue Jingmi Gongcheng/Optics and Precision Engineering, 2022, 30 (14): : 1764 - 1774
  • [24] Synthesis of Complex Sound Scenes with Transformation of Recorded Spatial Sound in Virtual Reality
    Pihlajamaki, Tapani
    Pulkki, Ville
    JOURNAL OF THE AUDIO ENGINEERING SOCIETY, 2015, 63 (7-8): : 542 - 551
  • [25] HADAD: A Lightweight Approach for Optimizing Hybrid Complex Analytics Queries
    Alotaibi, Rana
    Cautis, Bogdan
    Deutsch, Alin
    Manolescu, Ioana
    SIGMOD '21: PROCEEDINGS OF THE 2021 INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA, 2021, : 23 - 35
  • [26] Integrating Multihub Driven Attention Mechanism and Big Data Analytics for Virtual Representation of Visual Scenes
    Yao, Yang
    Gu, Bo
    Alazab, Mamoun
    Kumar, Neeraj
    Han, Yu
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2022, 18 (02) : 1435 - 1444
  • [27] A hybrid level-of-detail representation for large-scale urban scenes rendering
    Zhou, Shengchuan
    Yoo, Innfarn
    Benes, Bedrich
    Chen, Ge
    COMPUTER ANIMATION AND VIRTUAL WORLDS, 2014, 25 (3-4) : 245 - 255
  • [28] Detection and representation of scenes in videos
    Rasheed, Z
    Shah, M
    IEEE TRANSACTIONS ON MULTIMEDIA, 2005, 7 (06) : 1097 - 1105
  • [29] A Representation Method for Complex Road Networks in Virtual Geographic Environments
    Zheng, Peibei
    Tao, Hong
    Yue, Songshan
    Wu, Mingguang
    Lv, Guonian
    Zhou, Chuanlong
    ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION, 2017, 6 (11)
  • [30] Self-Supervised Representation Learning for Content Based Image Retrieval of Complex Scenes
    Govindarajan, Hariprasath
    Lindskog, Peter
    Lundstrom, Dennis
    Olmin, Amanda
    Roll, Jacob
    Lindsten, Fredrik
    2021 IEEE INTELLIGENT VEHICLES SYMPOSIUM WORKSHOPS (IV WORKSHOPS), 2021, : 249 - 256