Survey of Markov Chain Monte Carlo Methods in Light Transport Simulation

Šik, Martin; Křivánek, Jaroslav

doi:10.1109/tvcg.2018.2880455

Cited by 25 publications

(9 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To avoid using high resolution images, RT methods rely on environment map prefiltering [KVHS00], or analytical approximations, such as Spherical Harmonics (SH) [See66], and Spherical Gaussians (SG) [XSD * 13]. These methods allow for analytical evaluation of an environment map, as well as analytical sampling (directly in the case of SG, using Hierarchical Sampling for SH [JCJ09], or with lookup tables in [SK13]) and easy interpolation (useful when not enough samples can be requested). Still, they do not accurately represent complex HDR images commonly used when representing high–detailed light setups by using environment maps, and blend important light features in the original images, sometimes generating artifacts.…”

Section: Related Workmentioning

confidence: 99%

NEnv: Neural Environment Maps for Global Illumination

Rodríguez-Pardo

Fabre

Garcés

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

Environment maps are commonly used to represent and compute far‐field illumination in virtual scenes. However, they are expensive to evaluate and sample from, limiting their applicability to real‐time rendering. Previous methods have focused on compression through spherical‐domain approximations, or on learning priors for natural, day‐light illumination. These hinder both accuracy and generality, and do not provide the probability information required for importance‐sampling Monte Carlo integration. We propose NEnv, a deep‐learning fully‐differentiable method, capable of compressing and learning to sample from a single environment map. NEnv is composed of two different neural networks: A normalizing flow, able to map samples from uniform distributions to the probability density of the illumination, also providing their corresponding probabilities; and an implicit neural representation which compresses the environment map into an efficient differentiable function. The computation time of environment samples with NEnv is two orders of magnitude less than with traditional methods. NEnv makes no assumptions regarding the content (i.e. natural illumination), thus achieving higher generality than previous learning‐based approaches. We share our implementation and a diverse dataset of trained neural environment maps, which can be easily integrated into existing rendering engines.

show abstract

Section: Related Workmentioning

confidence: 99%

NEnv: Neural Environment Maps for Global Illumination

Rodríguez-Pardo

Fabre

Garcés

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…Монте-Карло интегрирования по схеме марковских цепей (Markov Chain Monte Carlo, MCMC) [1]. Обе группы методов в настоящее время успешно применяются для вычисления интеграла освещённости и решения так называемого уравнения рендеринга [2] и имеют свои плюсы и минусы.…”

Section: общая классификацияunclassified

“…Отличие от обычного MLT заключается в том, что после каждого шага цепи могут обменяться состояниями с некоторой вероятностью. Для того, чтобы такой обмен не нарушал стационарность распределения, вероятность должна вычисляться по формуле 5.6 [1]: репликами используется так называемая процедура закалки функций (function tempering [82]). Суть этой процедуры в том, чтобы применить к целевой функции преобразование следующего вида (формула 5.7):…”

Section: Replica Exchangeunclassified

“…Преимущества RELT (как и PMC) -лучшее исследование пространства интегрирования в глобальном смысле и лучшая параллелизуемость. Основным недостатком RELT в [1] считают тот факт, что сходимость сильно зависит от количества цепей, а это количество трудно подобрать правильно. С другой стороны, при реализации на GPU большое количество цепей не является проблемой.…”

Section: Replica Exchangeunclassified

“…Мы рекомендуем также ознакомиться с работой [1] для углублённого анализа методов расчёта освещения на основе MCMC. Эта работа подробно рассматривает принципы работы методов на основе Монте-Карло по схеме марковских цепей, и может служить в качестве отправной точки для понимания их на более глубоком уровне с целью практической реализации.…”

Section: дальнейшее изучение Mcmcunclassified

See 2 more Smart Citations

The current state of the methods for calculating global illumination in tasks of realistic computer graphics

Frolov¹,

Voloboi²,

Ершов³

et al. 2021

Proceedings of ISP RAS

View full text Add to dashboard Cite

Modern realistic computer graphics are based on light transport simulation. In this case, one of the main and difficult to calculate tasks is to calculate the global illumination, i.e. distribution of light in a virtual scene, taking into account multiple reflections and scattering of light and all kinds of its interaction with objects in the scene. Hundreds of publications and describing dozens of methods are devoted to this problem. In this state-of-the-art review, we would like not only to list and briefly describe these methods, but also to give some “map” of existing works, which will allow the reader to navigate, understand their advantages and disadvantages, and, thereby, choose a right method for themselves. Particular attention is paid to such characteristics of the methods as robustness and universality in relation to the used mathematical models, the transparency of the method verification, the possibility of efficient implementation on the GPU, as well as restrictions imposed on the scene or illumination phenomena. In contrast to the existing survey papers, not only the efficiency of the methods is analyzed, but also their limitations and the complexity of software implementation. In addition, we provide the results of our own numerical experiments with various methods that serve as illustrations for the conclusions.

show abstract

Monte Carlo: A flexible and accurate technique for modeling light transport in food and agricultural products

Sun

Yao

et al. 2020

Trends in Food Science & Technology

View full text Add to dashboard Cite

Survey of Markov Chain Monte Carlo Methods in Light Transport Simulation

Cited by 25 publications

References 51 publications

NEnv: Neural Environment Maps for Global Illumination

NEnv: Neural Environment Maps for Global Illumination

The current state of the methods for calculating global illumination in tasks of realistic computer graphics

Monte Carlo: A flexible and accurate technique for modeling light transport in food and agricultural products

Contact Info

Product

Resources

About