Delta radiance transfer

Loos, Bradford J.; Nowrouzezahrai, Derek; Jarosz, Wojciech; Sloan, Peter-Pike

doi:10.1145/2159616.2159648

Cited by 7 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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

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

show abstract

“…Zhou et al [ZHL*05] or Sun and Mukherjee [SM06]), where light transport representations are precomputed on some (potentially simplified) subset of the scene. We are inspired by Loos et al's “modular radiance transfer” [LAM*11, LNJS12] which precomputes compact transport operators for simple geometric shapes and then dynamically warps them to the actual scene, recomposing the total light transport on‐the‐fly. Zhao et al [ZHRB13] extended these ideas to volumetric transport in cloth expressed using exemplar voxel blocks.…”

Section: Related Workmentioning

confidence: 99%

Reduced Aggregate Scattering Operators for Path Tracing

Blumer

Novák

Habel

et al. 2016

Computer Graphics Forum

Self Cite

View full text Add to dashboard Cite

Equal-time comparisonPath tracing Ours Figure 1: Our reduced aggregate scattering operators (ASOs) compactly represent per-asset direct and indirect illumination, and the relation between them, in a reduced-dimensional subspace represented by a chain of dense matrices. ASOs can be used in path tracing to reduce the noise due to asset-internal scattering at the cost of a small amount of temporally stable bias. AbstractAggregate scattering operators (ASOs) describe the overall scattering behavior of an asset (i.e., an object or volume, or collection thereof) accounting for all orders of its internal scattering. We propose a practical way to precompute and compactly store ASOs and demonstrate their ability to accelerate path tracing. Our approach is modular avoiding costly and inflexible scene-dependent precomputation. This is achieved by decoupling light transport within and outside of each asset, and precomputing on a per-asset level. We store the internal transport in a reduced-dimensional subspace tailored to the structure of the asset geometry, its scattering behavior, and typical illumination conditions, allowing the ASOs to maintain good accuracy with modest memory requirements. The precomputed ASO can be reused across all instances of the asset and across multiple scenes. We augment ASOs with functionality enabling multi-bounce importance sampling, fast short-circuiting of complex light paths, and compact caching, while retaining rapid progressive preview rendering. We demonstrate the benefits of our ASOs by efficiently path tracing scenes containing many instances of objects with complex inter-reflections or multiple scattering.

show abstract

“…Sloan et al [2005] accounted for changes in local light transport arising from a more general set of deformations. More recent models allow discrete scenes to be composed without requiring additional precomputation [Loos et al 2011;Loos et al 2012], but do not allow for general continuous change in shape. In this paper, we focus on simulating low-frequency lighting effects and use radiosity [Goral et al 1984] as the global illumination algorithm.…”

Section: Related Workmentioning

confidence: 99%

Non-polynomial Galerkin projection on deforming meshes

et al. 2013

View full text Add to dashboard Cite

Figure 1: Our method enables reduced simulation of fluid flow around this flying bird over 2000 times faster than the corresponding full simulation and reduced radiosity computation in this architectural scene over 113 times faster than the corresponding full radiosity. AbstractThis paper extends Galerkin projection to a large class of nonpolynomial functions typically encountered in graphics. We demonstrate the broad applicability of our approach by applying it to two strikingly different problems: fluid simulation and radiosity rendering, both using deforming meshes. Standard Galerkin projection cannot efficiently approximate these phenomena. Our approach, by contrast, enables the compact representation and approximation of these complex non-polynomial systems, including quotients and roots of polynomials. We rely on representing each function to be model-reduced as a composition of tensor products, matrix inversions, and matrix roots. Once a function has been represented in this form, it can be easily model-reduced, and its reduced form can be evaluated with time and memory costs dependent only on the dimension of the reduced space.

show abstract

Delta radiance transfer

Cited by 7 publications

References 20 publications

NeRF‐Tex: Neural Reflectance Field Textures

NeRF‐Tex: Neural Reflectance Field Textures

Reduced Aggregate Scattering Operators for Path Tracing

Non-polynomial Galerkin projection on deforming meshes

Contact Info

Product

Resources

About