2013/06/28 by Vikash K. Mansinghka, Mansinghka, Vikash K., Tejas D. Kulkarni +6 · 1 citation
Computer Science · Mathematics · #Algorithms and Data Compression #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Generative Adversarial Networks and Image Synthesis #Machine Learning (stat.ML) #Statistics Education and Methodologies
paper · pdf · doi:10.48550/arxiv.1307.0060
openalex publication_date 2013/06/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The idea of computer vision as the Bayesian inverse problem to computer\ngraphics has a long history and an appealing elegance, but it has proved\ndifficult to directly implement. Instead, most vision tasks are approached via\ncomplex bottom-up processing pipelines. Here we show that it is possible to\nwrite short, simple probabilistic graphics programs that define flexible\ngenerative models and to automatically invert them to interpret real-world\nimages. Generative probabilistic graphics programs consist of a stochastic\nscene generator, a renderer based on graphics software, a stochastic likelihood\nmodel linking the renderer's output and the data, and latent variables that\nadjust the fidelity of the renderer and the tolerance of the likelihood model.\nRepresentations and algorithms from computer graphics, originally designed to\nproduce high-quality images, are instead used as the deterministic backbone for\nhighly approximate and stochastic generative models. This formulation combines\nprobabilistic programming, computer graphics, and approximate Bayesian\ncomputation, and depends only on general-purpose, automatic inference\ntechniques. We describe two applications: reading sequences of degraded and\nadversarially obscured alphanumeric characters, and inferring 3D road models\nfrom vehicle-mounted camera images. Each of the probabilistic graphics programs\nwe present relies on under 20 lines of probabilistic code, and supports\naccurate, approximately Bayesian inferences about ambiguous real-world images.\n