State-of-the-art Survey on Photorealistic Rendering of 3D Sences Based on Machine Learning

被引：0
|
作者：
Zhao Y.-Z. [1 ,2 ]
Wang L. [1 ,2 ]
Xu Y.-N. [1 ,2 ]
Zeng Z. [1 ,2 ]
Ge L.-S. [1 ,2 ]
Zhu J.-Q. [1 ,2 ]
Xu Z.-L. [1 ,2 ]
Zhao Y. [1 ,2 ]
Meng X.-X. [1 ,2 ]
机构：
[1] School of Software, Shandong University, Jinan
[2] Engineering Research Center of Digital Media Technology, Ministry of Education, Jinan
来源：
Ruan Jian Xue Bao/Journal of Software | 2022年 / 33卷 / 01期
基金：
中国国家自然科学基金;
关键词：
Global illumination; Machine learning; Monte Carlo noise reduction; Photorealistic rendering; Physics-based material model;
D O I：
10.13328/j.cnki.jos.006334
中图分类号：
学科分类号：
摘要：
Nowadays, the demand for photorealistic rendering in the movie, anime, game, and other industries is increasing, and the highly realistic rendering of 3D scenes usually requires a lot of calculation time and storage to calculate global illumination. How to ensure the quality of rendering on the premise of improving drawing speed is still one of the core and hot issues in the field of graphics. The data-driven machine learning method has opened up a new approach. In recent years, researchers have mapped a variety of highly realistic rendering methods to machine learning problems, thereby greatly reducing the computational cost. This article summarizes and analyzes the research progress of highly realistic rendering methods based on machine learning in recent years, including: global illumination optimization calculation methods based on machine learning, physical material modeling methods based on deep learning, and participatory media drawing method optimization based on deep learning, Monte Carlo denoising method based on machine learning, etc. This article discusses the mapping ideas of various drawing methods and machine learning methods in detail, summarizes the construction methods of network models and training data sets, and conducts comparative analysis on drawing quality, drawing time, network capabilities, and other aspects. Finally, this article proposes possible ideas and future prospects for the combination of machine learning and realistic rendering. © Copyright 2022, Institute of Software, the Chinese Academy of Sciences. All rights reserved.
引用
收藏
页码：356 / 376
页数：20
相关论文
共 70 条
  • [21] Granskog J, Rousselle F, Papas M, Novak J., Compositional neural scene representations for shading inference, ACM Transactions on Graphics, 39, 4, (2020)
  • [22] Rainer G, Jakob W, Ghosh A, Weyrich T., Neural BTF compression and interpolation, Computer Graphics Forum, 38, 2, pp. 235-244, (2019)
  • [23] Rainer G, Ghosh A, Jakob W, Weyrich T., Unified neural encoding of BTFs, Computer Graphics Forum, 39, 2, pp. 167-178, (2020)
  • [24] Hu BY, Guo J, Chen YJ, Li MT, Guo YW., DeepBRDF: A deep representation for manipulating measured BRDF, Computer Graphics Forum, 39, 2, pp. 157-166, (2020)
  • [25] Kuznetsov A, Hasan M, Xu ZX, Yan LQ, Walter B, Kalantari NK, Marschner S, Ramamoorthi R., Learning generative models for rendering specular microgeometry, ACM Transactions on Graphics, 38, 6, (2019)
  • [26] Che CQ, Luan FJ, Zhao S, Bala K, Gkioulekas I., Towards learning-based inverse subsurface scattering, Proc. of the 2020 IEEE Int'l Conf. on Computational Photography (ICCP), pp. 1-12, (2020)
  • [27] Currius RR, Dolonius D, Assarsson U, Sintorn E., Spherical gaussian light-field textures for fast precomputed global illumination, Computer Graphics Forum, 39, 2, pp. 133-146, (2020)
  • [28] Xin HG, Zheng SK, Xu K, Yan LQ., Lightweight bilateral convolutional neural networks for interactive single-bounce diffuse indirect illumination, IEEE Transactions on Visualization and Computer Graphics, (2020)
  • [29] Vorba J, Karlik O, Sik M, Ritschel T, Krivanek J., On-line learning of parametric mixture models for light transport simulation, ACM Transactions on Graphics, 33, 4, (2014)
  • [30] Herholz S, Elek O, Vorba J, Lensch H, Krivanek J., Product importance sampling for light transport path guiding, Computer Graphics Forum, 35, 6, pp. 67-77, (2016)
1234567