| 引用本文: | 赵烨梓,王璐,徐延宁,曾峥,葛亮昇,朱君秋,徐子林,赵钰,孟祥旭.基于机器学习的三维场景高度真实感绘制方法综述.软件学报,2022,33(1):356-376 |
| |
|
| |
|
|
| 本文已被：浏览 3412次 下载 8353次 |
码上扫一扫！ |
|
|
| 基于机器学习的三维场景高度真实感绘制方法综述 |
|
赵烨梓1,2, 王璐1,2, 徐延宁1,2, 曾峥1,2, 葛亮昇1,2, 朱君秋1,2, 徐子林1,2, 赵钰1,2, 孟祥旭1,2
|
|
1.山东大学 软件学院, 山东 济南 250101;2.数字媒体技术教育部工程研究中心, 山东 济南 250101
|
|
| 摘要: |
| 目前, 电影、动漫、游戏等产业对真实感绘制的需求越来越高, 而三维场景高度真实感绘制通常需要耗费大量的计算时间和存储空间来计算全局光照, 如何在保证绘制质量的前提下提升绘制速度依然是图形学领域面临的核心和热点问题之一. 数据驱动的机器学习方法开辟了一种新的研究思路, 近年来研究者将多种高度真实感绘制方法映射为机器学习问题, 从而大大降低了计算成本. 总结分析了近年来基于机器学习的高度真实感绘制方法的研究进展, 具体包括: 基于机器学习的全局光照优化计算方法、基于深度学习的物理材质建模方法、基于深度学习的参与性介质优化绘制方法、基于机器学习的蒙特卡洛降噪方法等. 详细论述了各种绘制方法与机器学习方法的映射思路, 归纳总结了网络模型以及训练数据集的构建方式, 并在绘制质量、绘制时间、网络能力等多个方面开展了对比分析. 最后, 本文提出了机器学习和真实感绘制相结合的可能思路和未来展望. |
| 关键词: 真实感绘制 机器学习 全局光照 基于物理的材质模型 蒙特卡洛降噪 |
| DOI：10.13328/j.cnki.jos.006334 |
| 分类号:TP309 |
| 基金项目:国家重点研发计划(2020YFB1708900); 国家自然科学基金(61872223); 山东省自然科学基金(ZR2020LZH016) |
|
| State-of-the-art Survey on Photorealistic Rendering of 3D Sences Based on Machine Learning |
|
ZHAO Ye-Zi1,2, WANG Lu1,2, XU Yan-Ning1,2, ZENG Zheng1,2, GE Liang-Sheng1,2, ZHU Jun-Qiu1,2, XU Zi-Lin1,2, ZHAO Yu1,2, MENG Xiang-Xu1,2
|
|
1.School of Software, Shandong University, Jinan 250101, China;2.Engineering Research Center of Digital Media Technology, Ministry of Education, Jinan 250101, China
|
| Abstract: |
| 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. |
| Key words: photorealistic rendering machine learning global illumination physics-based material model Monte Carlo noise reduction |
|
|
|
|
