ABSTRACT
Realistic image synthesis using path tracing needs many samples to achieve noise-free images. The noise is due to the use of Monte Carlo integration in path tracing. Since Monte Carlo integration evaluates each pixel using random sampling, we obtain noisy pixels at low sample counts. Due to the random nature of Monte Carlo integration, pixel values with finite numbers of samples can be significantly different, even if their correct solutions to the rendering equation are the same.
- Sadeghi, I., Chen, B., and Jensen, H. W. 2009. Coherent path tracing. journal of graphics, gpu, and game tools 14, 2, 33--43.Google Scholar
- Yee, H. 2004. A perceptual metric for production testing. journal of graphics, gpu, and game tools 9, 4, 33--40.Google Scholar
- Randomized coherent sampling for reducing perceptual rendering error
Recommendations
Reducing Sampling Error in Policy Gradient Learning
AAMAS '19: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent SystemsThis paper studies a class of reinforcement learning algorithms known as policy gradient methods. Policy gradient methods optimize the performance of a policy by estimating the gradient of the expected return with respect to the policy parameters. One ...
Perceptual Error Optimization for Monte Carlo Rendering
Synthesizing realistic images involves computing high-dimensional light-transport integrals. In practice, these integrals are numerically estimated via Monte Carlo integration. The error of this estimation manifests itself as conspicuous aliasing or ...
Antithetic sampling for Monte Carlo differentiable rendering
Stochastic sampling of light transport paths is key to Monte Carlo forward rendering, and previous studies have led to mature techniques capable of drawing high-contribution light paths in complex scenes. These sampling techniques have also been applied ...
Comments