A signal-processing framework for inverse rendering

By Ravi Ramamoorthi, P. Hanrahan. 2001

689 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

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

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

DreamFusion: Text-to-3D using 2D Diffusion (2022, neutral): “…ρ, assuming some point light source with 3D coordinate ℓ and color ℓρ, and an ambient light color ℓa, we render each point along the ray using diffuse reflectance (Lambert, 1760; Ramamoorthi & Hanrahan, 2001) to produce a color c for each point: c = ρ ◦ (ℓρ ◦max (0,n · (ℓ− µ)/ ∥ℓ− µ∥) + ℓa) .”
Neural Radiance Flow for 4D View Synthesis and Video Processing (2020, neutral): “Assuming that the incidental radiance is approximately the same at the object surface [55], the emitted diffuse color remains constant.”
Recognizing Materials Using Perceptually Inspired Features (2013, methodology): “…plastic , and paper 1999; Debevec et al. 2000; Matusik et al. 2000; Tom-inaga and Tanaka 2000; Boivin and Gagalowicz 2001; Nishino et al. 2001; Ramamoorthi and Hanrahan 2001; Cula et al. 2004; Debevec et al. 2004; Marschner et al. 2005; Pont and Koenderink 2005; Romeiro et al. 2008; Romeiro…”
Total variation models for variable lighting face recognition (2006, background): “The problem of obtaining R from an input image I is ill-posed [30].”
Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields (2021, neutral): “Prefiltered environment maps leverage the insight that the outgoing light from a surface can be seen as a spherical convolution of the incoming light and the (radially-symmetric) bidirectional reflectance distribution function (BRDF) that describes the material properties of the surface [28].”
Clustering appearances of objects under varying illumination conditions (2003, background): “For a Lambertian object, it has been proven that the set of all images taken under all lighting conditions forms a convex polyhedral cone in the image space [4], and this polyhedral cone can be approximated well by a low-dimensional linear subspace [2, 8, 20].”
NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis (2020, background): “The resulting Neural Reﬂectance and Visibility Field (NeRV) is visualized in Figure 3.”
Portrait shadow manipulation (2020, methodology): “l problem into two separate stages of detection and manipulation, these methods cannot recover from errors during the shadow detection step (Ma et al. 2016). General techniques for inverse rendering (Ramamoorthi and Hanrahan 2001; Sengupta et al. 2018) and intrinsic image decomposition (Barron and M”
InverseFaceNet: Deep Monocular Inverse Face Rendering (2017, methodology): “We thus represent the incident illumination on the face using second-order spherical harmonics (SH) [41, 45].”
Self-Supervised Multi-level Face Model Learning for Monocular Reconstruction at Over 250 Hz (2017, background): “Since the incident radiance is sufficiently smooth, an average error below 1% [46] can be achieved with only B = 3 bands independent of the illumination.”
Real-time shading-based refinement for consumer depth cameras (2014, methodology): “For Lambertian reflectance, the incident irradiance function is known to be smooth, and can be represented with only little error using the first nine spherical harmonics basis functions up to 2nd order [Ramamoorthi and Hanrahan 2001].”
FaceScape: A Large-Scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction (2020, methodology): “Under the assumption of Lambertian surfaces, we use the ﬁrst three bands of Spherical Harmonics(SH)[36] for illumination representation.”
NeRD: Neural Reflectance Decomposition from Image Collections (2020, background): “This problem is often referred to as inverse rendering [24, 41], where shape and material properties are estimated from a set of images, e.”