What is wrong?

Notice: Before sending an error with the download, please try the direct link first: Probabilistic Programming for Procedural Modeling and Design


You must sign in to do that.

Forgot password?

Probabilistic Programming for Procedural Modeling and Design

Probabilistic Programming for Procedural Modeling and Design

Probabilistic Programming for Procedural Modeling and Design

Score: ---- | 0 votes
| Sending vote
| Voted!

Book Details:

Publisher:Standford University
Pages:152 pages
Size:43.10 MB


Procedural modeling, or the use of pseudo-random programs to generate visual content, plays an important role in computer graphics and design. It facilitates content creation at massive scales, can automatically create painstakingly-detailed imagery, and can even generate pleasantly surprising results that can help people to navigate large and unintuitive design spaces.

Many procedural modeling applications demand directable content—the ability to enforce aesthetic or functional constraints on model output. Bayesian inference provides a framework for such control: the procedural model specifies a generative prior, with the constraints encoded as a likelihood function.

In this dissertation, we use probabilistic programming languages to express such Bayesian procedural models. A probabilistic programming language (PPL) provides random choice and Bayesian conditioning operators as primitives, and inference corresponds to searching the space of program executions for high-probability execution traces. PPLs can concisely express arbitrary probability distributions, including the complex, hierarchical, and often recursive stochastic processes required in procedural modeling.

Unfortunately, PPL inference is typically inefficient, relying on expensive Monte Carlo methods. This dissertation develops a suite a of techniques for speeding up PPL inference. First, we eliminate redundant computation from Metropolis-Hastings, one of the most commonly used PPL inference algorithms. Next, we show how to efficiently explore tightly-constrained design spaces using the gradient-based, Hamiltonian Monte Carlo algorithm. Then, we address the problems posed by deep branching structures in procedural models such as recursive trees, using a new variant of Sequential Monte Carlo. Finally, we make procedural modeling programs learn from their own outputs, using neural networks that guide programs toward high-probability results with fewer samples. Together, these tools bring PPL inference closer to interactive rates, which can enable more compelling graphics and design applications.



Loading comments...

Scanning lists...

The book in numbers

global rank

rank in categories

online since


rate score

Nothing yet...


Nothing yet...

Social likes

Nothing yet...



This may take several minutes


Countries segmentation

This may take several minutes

Source Referers

Websites segmentation


This may take several minutes