SkyGAN: Realistic Cloud Imagery for Image-based Lighting

被引:1
|
作者
Mirbauer, Martin [1 ]
Rittig, Tobias [1 ]
Iser, Tomas [1 ]
Krivanek, Jaroslav [1 ,2 ]
Sikudova, Elena [1 ]
机构
[1] Charles Univ Prague, Fac Math & Phys, Prague, Czech Republic
[2] Chaos Czech As, Prague, Czech Republic
关键词
modelling; natural phenomena; rendering; image-based rendering; atmospheric effects; MODEL;
D O I
10.1111/cgf.14990
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Achieving photorealism when rendering virtual scenes in movies or architecture visualizations often depends on providing a realistic illumination and background. Typically, spherical environment maps serve both as a natural light source from the Sun and the sky, and as a background with clouds and a horizon. In practice, the input is either a static high-resolution HDR photograph manually captured on location in real conditions, or an analytical clear sky model that is dynamic, but cannot model clouds. Our approach bridges these two limited paradigms: a user can control the sun position and cloud coverage ratio, and generate a realistically looking environment map for these conditions. It is a hybrid data-driven analytical model based on a modified state-of-the-art GAN architecture, which is trained on matching pairs of physically-accurate clear sky radiance and HDR fisheye photographs of clouds. We demonstrate our results on renders of outdoor scenes under varying time, date and cloud covers. Our source code and a dataset of 39 000 HDR sky images are publicly available at at https://github.com/CGGMFF/SkyGAN.
引用
收藏
页数:12
相关论文
共 50 条
  • [31] Image-Based Network Rendering of Large Meshes for Cloud Computing
    Okamoto, Yasuhide
    Oishi, Takeshi
    Ikeuchi, Katsushi
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2011, 94 (01) : 12 - 22
  • [32] Image-Based Network Rendering of Large Meshes for Cloud Computing
    Yasuhide Okamoto
    Takeshi Oishi
    Katsushi Ikeuchi
    International Journal of Computer Vision, 2011, 94 : 12 - 22
  • [33] A point cloud segmentation framework for image-based spatial transcriptomics
    Defard, Thomas
    Laporte, Hugo
    Ayan, Mallick
    Soulier, Juliette
    Curras-Alonso, Sandra
    Weber, Christian
    Massip, Florian
    Londono-Vallejo, Jose-Arturo
    Fouillade, Charles
    Mueller, Florian
    Walter, Thomas
    COMMUNICATIONS BIOLOGY, 2024, 7 (01)
  • [34] ASTERI: image-based representation of EEG signals for motor imagery classification
    Gomes J.C.
    Rodrigues M.C.A.
    dos Santos W.P.
    Research on Biomedical Engineering, 2022, 38 (02) : 661 - 681
  • [35] How the image influences human action and what the role is of lighting in a new image-based culture
    Baranowski, Pawel
    PRZEGLAD ELEKTROTECHNICZNY, 2012, 88 (4A): : 223 - 226
  • [36] Real-time image-based lighting of metallic and pearlescent car paints
    Kneiphof, Tom
    Klein, Reinhard
    COMPUTERS & GRAPHICS-UK, 2022, 105 : 36 - 45
  • [37] Evalution of High Dynamic Range Image-Based Sky Models in Lighting Simulation
    Inanici, Mehlika
    LEUKOS, 2010, 7 (02) : 69 - 84
  • [38] Performance comparison of techniques for approximating image-based lighting by directional light sources
    Madsen, Claus B.
    Laursen, Rune E.
    IMAGE ANALYSIS, PROCEEDINGS, 2007, 4522 : 888 - +
  • [39] Research on An Image-based Visual Positioning System in the PDP Lighting Inspection Machine
    Yang, Lei
    Liu, Gui-xi
    Chang, Peng-ju
    EQUIPMENT MANUFACTURING TECHNOLOGY AND AUTOMATION, PTS 1-3, 2011, 317-319 : 865 - +
  • [40] Evaluation of an image-based talking head with realistic facial expression and head motion
    Kang Liu
    Joern Ostermann
    Journal on Multimodal User Interfaces, 2012, 5 : 37 - 44