Efficient Specular Glints Rendering With Differentiable Regularization

Fan, Jiahui; Wang, Beibei; Wu, Wenshi; Hašan, Miloš; Yang, Jian; Yan, Ling‐Qi

doi:10.1109/tvcg.2022.3144479

Cited by 3 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Surface variation of optical properties, however, can only roughly approximate the 3D variation of the properties in a heterogeneous translucent object. A bidirectional texture function (BTF) [DVGNK99, RGJW20, KMX*21, KWM*22, FWH*23] is a bidirectional reflectance distribution function (BRDF) spatially extended to a flat textured patch of surface geometry. As opposed to a spatially varying BRDF, which assumes that light is incident and observed in the same surface position, a BTF can include subsurface scattering within the patch.…”

Section: Related Workmentioning

confidence: 99%

Neural SSS: Lightweight Object Appearance Representation

TG,

Tran,

Jensen

et al. 2024

Computer Graphics Forum

View full text Add to dashboard Cite

We present a method for capturing the BSSRDF (bidirectional scattering‐surface reflectance distribution function) of arbitrary geometry with a neural network. We demonstrate how a compact neural network can represent the full 8‐dimensional light transport within an object including heterogeneous scattering. We develop an efficient rendering method using importance sampling that is able to render complex translucent objects under arbitrary lighting. Our method can also leverage the common planar half‐space assumption, which allows it to represent one BSSRDF model that can be used across a variety of geometries. Our results demonstrate that we can render heterogeneous translucent objects under arbitrary lighting and obtain results that match the reference rendered using volumetric path tracing.

show abstract

Section: Related Workmentioning

confidence: 99%

Neural SSS: Lightweight Object Appearance Representation

TG,

Tran,

Jensen

et al. 2024

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

A Tiny Example Based Procedural Model for Real-Time Glinty Appearance Rendering

Xing,

Tan,

et al. 2024

J. Comput. Sci. Technol.

View full text Add to dashboard Cite

Efficient participating media rendering with differentiable regularization

Wu,

Wang,

Hašan

et al. 2024

Comp. Visual Media

View full text Add to dashboard Cite

Highly scattering media, such as milk, skin, and clouds, are common in the real world. Rendering participating media is challenging, especially for high-order scattering dominant media, because the light may undergo a large number of scattering events before leaving the surface. Monte Carlo-based methods typically require a long time to produce noise-free results. Based on the observation that low-albedo media contain less noise than high-albedo media, we propose reducing the variance of the rendered results using differentiable regularization. We first render an image with low-albedo participating media together with the gradient with respect to the albedo, and then predict the final rendered image with a low-albedo image and gradient image via a novel prediction function. To achieve high quality, we also consider the gradients of neighboring frames to provide a noise-free gradient image. Ultimately, our method can produce results with much less overall error than equal-time path tracing methods.

show abstract

Efficient Specular Glints Rendering With Differentiable Regularization

Cited by 3 publications

References 28 publications

Neural SSS: Lightweight Object Appearance Representation

Neural SSS: Lightweight Object Appearance Representation

A Tiny Example Based Procedural Model for Real-Time Glinty Appearance Rendering

Efficient participating media rendering with differentiable regularization

Contact Info

Product

Resources

About