Markov random field

About: Markov random field is a research topic. Over the lifetime, 5669 publications have been published within this topic receiving 179568 citations. The topic is also known as: MRF.

Monocular Object Instance Segmentation and Depth Ordering with CNNs

Abstract: In this paper we tackle the problem of instance-level segmentation and depth ordering from a single monocular image. Towards this goal, we take advantage of convolutional neural nets and train them to directly predict instance-level segmentations where the instance ID encodes the depth ordering within image patches. To provide a coherent single explanation of an image we develop a Markov random field which takes as input the predictions of convolutional neural nets applied at overlapping patches of different resolutions, as well as the output of a connected component algorithm. It aims to predict accurate instance-level segmentation and depth ordering. We demonstrate the effectiveness of our approach on the challenging KITTI benchmark and show good performance on both tasks.

Integration of vision modules and labeling of surface discontinuities

Abstract: It is assumed that a major goal of the early vision modules and their integration is to deliver a cartoon of the discontinuities in the scene and to label them in terms of their physical origin. The output of each of the vision modules is noisy, possibly sparse, and sometimes not unique. The authors suggest the use of a coupled Markov random field (MRF) at the output of each module (image cues)-stereo, motion, color, and texture-to achieve two goals: first, to counteract the noise and fill in sparse data, and secondly, to integrate the image within each MRF to find the module discontinuities and align them with the intensity edges. The authors outline a theory of how to label the discontinuities in terms of depth, orientation, albedo, illumination, and specular discontinuities. They present labeling results using a simple linear classifier operating on the output of the MRF associated with each vision module and coupled to the image data. The classifier has been trained on a small set of a mixture of synthetic and real data. >

Mutually compatible Gibbs random fields

Abstract: A unified theory for the mathematical description of Gibbs random fields that answers some important theoretical and practical questions about their statistical behavior is presented. The local transfer function is introduced, and the joint probability measure of the general Gibbs random field is derived in terms of this function. The resulting probability structure is required to satisfy the property of mutual compatibility. A necessary and sufficient condition for a Gibbs random field to be mutually compatible is developed and used to prove that a mutually compatible Gibbs random field is a unilateral Markov random field. The existence of some special nontrivial cases of Gibbs random fields that are mutually compatible is demonstrated. Conditions on the translation invariance and isotropy of the general Gibbs random field with a free boundary are studied. The class of Gibbs random fields with a homogeneous local transfer function and the class of horizontally and vertically translation-invariant Gibbs random fields are introduced and treated. The concept of a translation-invariant Gibbs random field is also explored. The problem of the statistical inference of mutually compatible Gibbs random fields is discussed. >

A Feature-based Approach for Dense Segmentation and Estimation of Large Disparity Motion

Abstract: We present a novel framework for motion segmentation that combines the concepts of layer-based methods and feature-based motion estimation. We estimate the initial correspondences by comparing vectors of filter outputs at interest points, from which we compute candidate scene relations via random sampling of minimal subsets of correspondences. We achieve a dense, piecewise smooth assignment of pixels to motion layers using a fast approximate graphcut algorithm based on a Markov random field formulation. We demonstrate our approach on image pairs containing large inter-frame motion and partial occlusion. The approach is efficient and it successfully segments scenes with inter-frame disparities previously beyond the scope of layer-based motion segmentation methods. We also present an extension that accounts for the case of non-planar motion, in which we use our planar motion segmentation results as an initialization for a regularized Thin Plate Spline fit. In addition, we present applications of our method to automatic object removal and to structure from motion.