# Approximate Bayesian Image Interpretation using Generative Probabilistic Graphics Programs

arXiv: https://arxiv.org/abs/1307.0060 · HTML: https://mlsanity.com/paper/1307.0060/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2013.

## Built on by (most cited first, 10 of 10)

- [Neural Articulated Radiance Field](https://mlsanity.com/paper/2104.03110/) (2021)
- [Can Large Language Models Understand Symbolic Graphics Programs?](https://mlsanity.com/paper/2408.08313/) (2024)
- [3DP3: 3D Scene Perception via Probabilistic Programming](https://mlsanity.com/paper/2111.00312/) (2021)
- [Designing Perceptual Puzzles by Differentiating Probabilistic Programs](https://mlsanity.com/paper/2204.12301/) (2022)
- [ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Images](https://mlsanity.com/paper/2210.17415/) (2022)
- [3D Neural Embedding Likelihood: Probabilistic Inverse Graphics for Robust 6D Pose Estimation](https://mlsanity.com/paper/2302.03744/) (2023)
- [Meta-simulation for the Automated Design of Synthetic Overhead Imagery](https://mlsanity.com/paper/2209.08685/) (2022)
- [Differentiable Rendering for Pose Estimation in Proximity Operations](https://mlsanity.com/paper/2212.12668/) (2022)
- [GenMatter: Perceiving Physical Objects with Generative Matter Models](https://mlsanity.com/paper/2604.22160/) (2026)
- [PaintCopilot: Modeling Painting as Autonomous Artistic Continuation](https://mlsanity.com/paper/2605.20941/) (2026)

## Abstract (arXiv)

The idea of computer vision as the Bayesian inverse problem to computer graphics has a long history and an appealing elegance, but it has proved difficult to directly implement. Instead, most vision tasks are approached via complex bottom-up processing pipelines. Here we show that it is possible to write short, simple probabilistic graphics programs that define flexible generative models and to automatically invert them to interpret real-world images. Generative probabilistic graphics programs consist of a stochastic scene generator, a renderer based on graphics software, a stochastic likelihood model linking the renderer's output and the data, and latent variables that adjust the fidelity of the renderer and the tolerance of the likelihood model. Representations and algorithms from computer graphics, originally designed to produce high-quality images, are instead used as the deterministic backbone for highly approximate and stochastic generative models. This formulation combines probabilistic programming, computer graphics, and approximate Bayesian computation, and depends only on general-purpose, automatic inference techniques. We describe two applications: reading sequences of degraded and adversarially obscured alphanumeric characters, and inferring 3D road models from vehicle-mounted camera images. Each of the probabilistic graphics programs we present relies on under 20 lines of probabilistic code, and supports accurate, approximately Bayesian inferences about ambiguous real-world images.