DeepAI AI Chat
Log In Sign Up

The Informed Sampler: A Discriminative Approach to Bayesian Inference in Generative Computer Vision Models

by   Varun Jampani, et al.

Computer vision is hard because of a large variability in lighting, shape, and texture; in addition the image signal is non-additive due to occlusion. Generative models promised to account for this variability by accurately modelling the image formation process as a function of latent variables with prior beliefs. Bayesian posterior inference could then, in principle, explain the observation. While intuitively appealing, generative models for computer vision have largely failed to deliver on that promise due to the difficulty of posterior inference. As a result the community has favoured efficient discriminative approaches. We still believe in the usefulness of generative models in computer vision, but argue that we need to leverage existing discriminative or even heuristic computer vision methods. We implement this idea in a principled way with an "informed sampler" and in careful experiments demonstrate it on challenging generative models which contain renderer programs as their components. We concentrate on the problem of inverting an existing graphics rendering engine, an approach that can be understood as "Inverse Graphics". The informed sampler, using simple discriminative proposals based on existing computer vision technology, achieves significant improvements of inference.


page 8

page 10

page 15

page 16

page 18


Informed MCMC with Bayesian Neural Networks for Facial Image Analysis

Computer vision tasks are difficult because of the large variability in ...

Approximate Bayesian Image Interpretation using Generative Probabilistic Graphics Programs

The idea of computer vision as the Bayesian inverse problem to computer ...

Vision System for AGI: Problems and Directions

What frameworks and architectures are necessary to create a vision syste...

Inverse Graphics with Probabilistic CAD Models

Recently, multiple formulations of vision problems as probabilistic inve...

Inference with Discriminative Posterior

We study Bayesian discriminative inference given a model family p(c,, θ)...

Learning Beyond Human Expertise with Generative Models for Dental Restorations

Computer vision has advanced significantly that many discriminative appr...

Simulations for Validation of Vision Systems

As the computer vision matures into a systems science and engineering di...