Precomputed Radiance Transfer for Real-Time Rendering in Dynamic, Low-Frequency Lighting Environments

By Peter-Pike J. Sloan, Jan Kautz, John M. Snyder. International Conference on Computer Graphics and Interactive Techniques, 2002

1,176 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/acd57c79ef5385c7e04f08b126135bccaa6974cc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Ambient Occlusion and Edge Cueing for Enhancing Real Time Molecular Visualization (2006, background): “For the case of atoms, this signal is defined over spheres, so it would be possible to store it, in a conveniently compact way, as a small set of spherical harmonic coefficients [29] per atom.”
NeRF: Representing scenes as neural radiance ﬁelds for view synthesis (neutral): “Though rarely cited, this parallels the development two decades ago of compact representations for light transport and precomputed radiance transfer (PRT) [ 64 ], in which the author of this article played a major role [ 53 ].”
Baking Neural Radiance Fields for Real-Time View Synthesis (2021, background): “It is also possible to bake view-dependent colors — the field of precomputed radiance transfer explores spherical basis functions [43, 33, 49] suitable for this purpose.”
To appear in the ACM SIGGRAPH conference proceedings Modular Bases for Fluid Dynamics (positive): “Model reduction has been used in a number of other branches of graphics including nonlinear deformation [James and Fatahalian 2003], finite element methods [Barbič and James 2005], and precomputed radiance transfer [Sloan et al. 2002].”
3D Morphable Face Models—Past, Present, and Future (2019, neutral): “Themost complex global model of appearance considered in the context of 3DMMs is the precomputed radiance transfer (PRT) model [Sloan et al. 2002].”
Plenoxels: Radiance Fields without Neural Networks (2021, background): “Spherical harmonics are a standard basis for functions over the sphere, and have been used previously to represent view dependence [4, 36, 47, 58, 59].”
PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization (2020, methodology): “We split the dataset into a training set of 450 subjects and a test set of 50 subjects and render the meshes with precomputed radiance transfer [38] using 163 second-order spherical harmonics from HDRI Haven(1).”
FAUST: Dataset and Evaluation for 3D Mesh Registration (2014, background): “Given a generic scan surface point x, its color ix and its albedo ax are related as: ix = (τx · lSH)ax.”
Skinning mesh animations (2005, methodology): “For example, in our implementation, we generate diffuse Precomputed Radiance Transfer (PRT) [Sloan et al. 2002] for SMAs (and translating ground planes).”
NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis (2020, methodology): “Our method is inspired by a long line of work in graphics that explores precomputation [42, 52] and approximation [6, 14, 41, 43] strategies to efficiently compute global illumination in physically-based rendering.”
PlenOctrees for Real-time Rendering of Neural Radiance Fields (2021, methodology): “Other than SHs, we also experiment with Spherical Gaussians (SG) [8], a learnable spherical basis which have been used to represent all-frequency lighting [54, 46, 21].”
Acquiring linear subspaces for face recognition under variable lighting (2005, background): “In this section, we briefly summarize the recent work presented in [2], [14], [15], [19].”
NeX: Real-time View Synthesis with Neural Basis Expansion (2021, methodology): “Our reparameterization of pixel into a combination of basis functions is closely related to light field factorization approaches in many areas, such as surface light field [48], precomputed radiance transfer [36, 35], BRDF estimations [11], light field and tensor display [46].”