Multilayer feedforward networks are universal approximators
Neural Networks
Connectionist learning procedures
Artificial Intelligence
Approximation theory and feedforward networks
Neural Networks
Measuring and modeling anisotropic reflection
SIGGRAPH '92 Proceedings of the 19th annual conference on Computer graphics and interactive techniques
Radiosity and realistic image synthesis
Radiosity and realistic image synthesis
Proceedings of the 24th annual conference on Computer graphics and interactive techniques
NeuroAnimator: fast neural network emulation and control of physics-based models
Proceedings of the 25th annual conference on Computer graphics and interactive techniques
Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Clustered principal components for precomputed radiance transfer
ACM SIGGRAPH 2003 Papers
Machine Learning for Computer Graphics: A Manifesto and Tutorial
PG '03 Proceedings of the 11th Pacific Conference on Computer Graphics and Applications
Triple product wavelet integrals for all-frequency relighting
ACM SIGGRAPH 2004 Papers
Precomputed local radiance transfer for real-time lighting design
ACM SIGGRAPH 2005 Papers
View-dependent precomputed light transport using nonlinear Gaussian function approximations
I3D '06 Proceedings of the 2006 symposium on Interactive 3D graphics and games
Splatting indirect illumination
I3D '06 Proceedings of the 2006 symposium on Interactive 3D graphics and games
I3D '06 Proceedings of the 2006 symposium on Interactive 3D graphics and games
Accurate Direct Illumination Using Iterative Adaptive Sampling
IEEE Transactions on Visualization and Computer Graphics
All-frequency relighting of glossy objects
ACM Transactions on Graphics (TOG)
Direct-to-indirect transfer for cinematic relighting
ACM SIGGRAPH 2006 Papers
Implicit visibility and antiradiance for interactive global illumination
ACM SIGGRAPH 2007 papers
Key Point Subspace Acceleration and soft caching
ACM SIGGRAPH 2007 papers
Interactive Global Illumination Using Implicit Visibility
PG '07 Proceedings of the 15th Pacific Conference on Computer Graphics and Applications
A meshless hierarchical representation for light transport
ACM SIGGRAPH 2008 papers
Imperfect shadow maps for efficient computation of indirect illumination
ACM SIGGRAPH Asia 2008 papers
An efficient GPU-based approach for interactive global illumination
ACM SIGGRAPH 2009 papers
Hardware-accelerated global illumination by image space photon mapping
Proceedings of the Conference on High Performance Graphics 2009
Precomputation-Based Rendering
Foundations and Trends® in Computer Graphics and Vision
Cascaded light propagation volumes for real-time indirect illumination
Proceedings of the 2010 ACM SIGGRAPH symposium on Interactive 3D Graphics and Games
OptiX: a general purpose ray tracing engine
ACM SIGGRAPH 2010 papers
Interactive Indirect Illumination Using Adaptive Multiresolution Splatting
IEEE Transactions on Visualization and Computer Graphics
Voxel-based global illumination
I3D '11 Symposium on Interactive 3D Graphics and Games
Analyzing Visibility Configurations
IEEE Transactions on Visualization and Computer Graphics
The State of the Art in Interactive Global Illumination
Computer Graphics Forum
Training feedforward networks with the Marquardt algorithm
IEEE Transactions on Neural Networks
All-frequency precomputed radiance transfer for glossy objects
EGSR'04 Proceedings of the Fifteenth Eurographics conference on Rendering Techniques
Precomputed radiance transfer for real-time indirect lighting using a spectral mesh basis
EGSR'07 Proceedings of the 18th Eurographics conference on Rendering Techniques
Wavelet radiance transport for interactive indirect lighting
EGSR'06 Proceedings of the 17th Eurographics conference on Rendering Techniques
A practical algorithm for rendering interreflections with all-frequency BRDFs
ACM Transactions on Graphics (TOG)
| Hi-index | 0.00 |
We present radiance regression functions for fast rendering of global illumination in scenes with dynamic local light sources. A radiance regression function (RRF) represents a non-linear mapping from local and contextual attributes of surface points, such as position, viewing direction, and lighting condition, to their indirect illumination values. The RRF is obtained from precomputed shading samples through regression analysis, which determines a function that best fits the shading data. For a given scene, the shading samples are precomputed by an offline renderer. The key idea behind our approach is to exploit the nonlinear coherence of the indirect illumination data to make the RRF both compact and fast to evaluate. We model the RRF as a multilayer acyclic feed-forward neural network, which provides a close functional approximation of the indirect illumination and can be efficiently evaluated at run time. To effectively model scenes with spatially variant material properties, we utilize an augmented set of attributes as input to the neural network RRF to reduce the amount of inference that the network needs to perform. To handle scenes with greater geometric complexity, we partition the input space of the RRF model and represent the subspaces with separate, smaller RRFs that can be evaluated more rapidly. As a result, the RRF model scales well to increasingly complex scene geometry and material variation. Because of its compactness and ease of evaluation, the RRF model enables real-time rendering with full global illumination effects, including changing caustics and multiple-bounce high-frequency glossy interreflections.