Stanford CS348B, Spring 2022

IMAGE SYNTHESIS TECHNIQUES

This page contains lecture slides and recommended readings for the Spring 2022 offering of CS348B.

(How advanced image synthesis is used in the real world, review of ray tracing basics)

Further Reading:

(Representing rays, ray-object intersection methods, acceleration structures, pbrt basics)

Further Reading:

(how to build acceleration structures efficiently (two-level, refitting, incremental builds), advanced primitive types, tessellation, numerical precision issues)

Further Reading:

(Definition of radiometric quantities, the light field, integrating total energy falling on surfaces)

Further Reading:

(Sampling from distributions and shapes, numerical estimation of illumination)

Further Reading:

(Basics of how lenses and sensors work, motion blur and depth of field)

(Primal and Fourier space representations of signals, convolution theorem, sampling theorem, aliasing and anti-aliasing)

Further Reading:

(BRDFs, the reflection equation, basic reflection models)

Further Reading:

(Monte Carlo estimation of the reflection equation, sampling lights and BRDFs)

Further Reading:

(Monte Carlo variance reduction techniques, stratified sampling, importance sampling)

Further Reading:

(The rendering equation, path tracing, Russian roulette, path guiding)

(Light tracing, bidirectional path tracing, photon mapping)

(Scattering and phase functions, the volume rendering equation, null scattering)

(Anisotropic surfaces, subsurface scattering)

(Algorithms for reducing variance at low sampling count (ReSTIR), conventional and DNN-based denoising)

(Discrepancy and Quasi-Monte Carlo, low-discrepancy constructions, spectral analysis of sampling)

(Three parts:
(1) guided sampling [Kayvon & Vishnu],
(2) warped rendering [Doug], and
(3) course wrap-up [Matt] (on-going research and how to get involved).)