Learning Rich Statistical Models of the Visual World for Robust Perception

强大的情报依赖于对丢失、不完整、模棱两可和损坏的数据进行推理的能力。这在视觉感知中尤其如此，在视觉感知中，智能系统面临着只给出二维图像就不断变化的三维世界的复杂性进行推理的问题。贝叶斯推理已经成为处理这类问题的流行方法，因为它提供了一种将模糊的传感器测量与关于世界的先验知识相结合的可靠方法。先验表示感知系统收集的经验，通过以统计合理的方式整合不同的信息源，使这样的系统能够稳健地响应新的情况。马尔可夫随机场(MRF)为表示视觉先验提供了一种强大而流行的形式。然而，他们通常只对局部的成对像素交互进行建模，这限制了他们的建模能力。该项目旨在使用更大的像素邻域(集团)来提高这些模型的能力和适用性。所提出的专家领域(FOE)模型推广了许多已有的马尔可夫随机场模型，其所有参数都可以从真实的训练数据中学习。例如，初步实验表明，图像重建应用受益于这种更丰富的视觉先验，但许多其他应用领域仍未被探索。这些统计建模工具的开发还将对机器视觉以外的其他领域产生影响，这些领域需要对复杂的高维数据进行建模。最后，收集的实验数据、学习到的模型和软件的传播有望刺激研究，并使定量比较成为可能，从而获得更好的视觉世界统计模型。

Robust intelligence rests on the ability to reason about missing, incomplete, ambiguous and corrupted data. This is particularly true in visual perception, where an intelligent system is faced with reasoning about the complexity of a changing three-dimensional world given only two-dimensional images. Bayesian inference has become popular for dealing with such problems because it provides a sound way of combining ambiguous sensor measurements with prior knowledge about the world. Priors represent the collected experience of a perceptual system and by integrating heterogeneous sources of information in a statistically sound way enable such a system to respond robustly to novel situations.Markov random fields (MRFs) provide a powerful and popular formalism for representing visual priors. However, they have typically modeled only local, pairwise pixel interactions, which limit their modeling capabilities. This project aims at increasing the power and applicability of these models using larger pixel neighborhoods (cliques). The proposed Fields-of-Experts (FoE) model generalizes many previous MRF models, and all its parameters can be learned from real-world training data. Preliminary experiments have shown that, for example, image reconstruction applications benefit from such richer visual priors, but many other application domains have remained unexplored. The development of these statistical modeling tools will also have an impact on other domains outside of machine vision where the need for modeling complex, high-dimensional data arises. Finally, the dissemination of the collected experimental data, learned models, and software promises to stimulate research and make possible quantitative comparisons towards better statistical models of the visual world.