Neural rendering algorithms introduce a fundamentally new approach for photorealistic rendering, typically by learning a neural representation of illumination on large numbers of ground truth images. When training for a given variable scene, such as changing objects, materials, lights, and viewpoint, the space \( \mathcal {D} \) of possible training data instances quickly becomes unmanageable as the dimensions of variable parameters increase. We introduce a novel Active Exploration method using Markov Chain Monte Carlo, which explores \( \mathcal {D} \) , generating samples (i.e., ground truth renderings) that best help training and interleaves training and on-the-fly sample data generation. We introduce a self-tuning sample reuse strategy to minimize the expensive step of rendering training samples. We apply our approach on a neural generator that learns to render novel scene instances given an explicit parameterization of the scene configuration. Our results show that Active Exploration trains our network much more efficiently than uniformly sampling and, together with our resolution enhancement approach, achieves better quality than uniform sampling at convergence. Our method allows interactive rendering of hard light transport paths (e.g., complex caustics), which require very high samples counts to be captured, and provides dynamic scene navigation and manipulation, after training for 5 to 18 hours depending on required quality and variations.

Stavros Diolatzis

Julien Philip

George Drettakis

ACM Transactions on Graphics

ACM TRANSACTIONS ON GRAPHICS (TOG) 是一份经过同行评审的科学期刊，旨在传播计算机图形学领域的最新发现。它自 1982 年以来由计算机协会出版。从 2003 年开始，所有在 SIGGRAPH 年度会议上被接受发表的论文都印在该期刊的夏季特刊上。

ACM Transactions on Graphics (TOG) is a peer-reviewed scientific journal aimed at disseminating the latest research findings in the field of computer graphics. It has been published by the Association for Computing Machinery since 1982. Since 2003, all papers accepted for presentation at the SIGGRAPH annual conference are included in the summer issue of this journal.

《ACM Transactions on Graphics》（TOG）是一本经过同行评审的科学期刊，旨在传播计算机图形学领域的最新研究成果。该期刊自1982年由计算机协会出版。从2003年起，所有在SIGGRAPH年度会议上接受发表的论文均会收录在该期刊的夏季特刊中。

ACM Trans. Graph.

Active Exploration for Neural Global Illumination of Variable Scenes

This work introduces a novel Active Exploration method using Markov Chain Monte Carlo, which explores samples that best help training and interleaves training and on-the-fly sample data generation, and introduces a self-tuning sample reuse strategy to minimize the expensive step of rendering training samples.

Category	Quartile
计算机科学	1
计算机科学, 计算机软件工程	1

Active Exploration for Neural Global Illumination of Variable Scenes

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info

Category	Quartile
COMPUTER SCIENCE, SOFTWARE ENGINEERING	1