Reduced Aggregate Scattering Operators for Path Tracing

Blumer, Adrian; Novák, Jan; Habel, Ralf; Nowrouzezahrai, Derek; Jarosz, Wojciech

doi:10.1111/cgf.13043

Cited by 5 publications

(3 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, we believe that the ideas we present in this work can be used for other path tracing and physically based rendering problems, like aggregate scattering [BNH * 16] or BxDF representations [SRRW21, CNN22, ZLW * 21, CLZ * 20]. We hope our work inspires future work on invertible neural generative models for physically‐based and neural rendering.…”

Section: Discussionmentioning

confidence: 87%

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: Discussionmentioning

confidence: 87%

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

“…Some alternative approaches represent only the phase function [GFWF20] (in addition to density), while others learn transmittances and simplified airlight integrals [SDZ*21]; the optimal approach is still actively sought. Furthermore, current NeRF approaches, including ours, march through the module(s) instead of learning the transport between points on the boundary, as proposed in many traditional modular approaches [LAM*11, LNJS12, ZHRB13, BNH*16]. This incurs higher cost: The MLP is evaluated multiple times, but it also factors out a large portion of the view dependency to facilitate accurate directional reconstruction.…”

Section: Future Workmentioning

confidence: 99%

NeRF‐Tex: Neural Reflectance Field Textures

Baatz

Granskog

Papas

et al. 2022

Computer Graphics Forum

View full text Add to dashboard Cite

We investigate the use of neural fields for modelling diverse mesoscale structures, such as fur, fabric and grass. Instead of using classical graphics primitives to model the structure, we propose to employ a versatile volumetric primitive represented by a neural reflectance field (NeRF-Tex), which jointly models the geometry of the material and its response to lighting. The NeRF-Tex primitive can be instantiated over a base mesh to 'texture' it with the desired meso and microscale appearance. We condition the reflectance field on user-defined parameters that control the appearance. A single NeRF texture thus captures an entire space of reflectance fields rather than one specific structure. This increases the gamut of appearances that can be modelled and provides a solution for combating repetitive texturing artifacts. We also demonstrate that NeRF textures naturally facilitate continuous level-of-detail rendering. Our approach unites the versatility and modelling power of neural networks with the artistic control needed for precise modelling of virtual scenes. While all our training data are currently synthetic, our work provides a recipe that can be further extended to extract complex, hard-to-model appearances from real images.

show abstract

“…PRT Optimized for Lighting Scenarios. Closest to our work are Modular Radiance Transfer (MRT) [Loos et al 2011] and Reduced Aggregate Scattering Operators (RASO) [Blumer et al 2016]. Both used a custom lighting scenario to obtain better basis representation for direct illumination.…”

Section: Previous Workmentioning

confidence: 99%

A Data-Driven Paradigm for Precomputed Radiance Transfer

Belcour¹,

Deliot²,

Wilhem³

et al. 2022

Proc. ACM Comput. Graph. Interact. Tech.

View full text Add to dashboard Cite

In this work, we explore a change of paradigm to build Precomputed Radiance Transfer (PRT) methods in a data-driven way. This paradigm shift allows us to alleviate the difficulties of building traditional PRT methods such as defining a reconstruction basis, coding a dedicated path tracer to compute a transfer function, etc. Our objective is to pave the way for Machine Learned methods by providing a simple baseline algorithm. More specifically, we demonstrate real-time rendering of indirect illumination in hair and surfaces from a few measurements of direct lighting. We build our baseline from pairs of direct and indirect illumination renderings using only standard tools such as Singular Value Decomposition (SVD) to extract both the reconstruction basis and transfer function.

show abstract

Reduced Aggregate Scattering Operators for Path Tracing

Cited by 5 publications

References 59 publications

NEnv: Neural Environment Maps for Global Illumination

NEnv: Neural Environment Maps for Global Illumination

NeRF‐Tex: Neural Reflectance Field Textures

A Data-Driven Paradigm for Precomputed Radiance Transfer

Contact Info

Product

Resources

About