28 Result(s)
-
Chapter and Conference Paper
Learning Shape Analysis
We present a data-driven verification framework to automatically prove memory safety of heap-manipulating programs. Our core contribution is a novel statistical machine learning technique that maps observed pr...
-
Chapter and Conference Paper
Deep Disentangled Representations for Volumetric Reconstruction
We introduce a convolutional neural network for inferring a compact disentangled graphical description of objects from 2D images that can be used for volumetric reconstruction. The network comprises an encoder...
-
Chapter and Conference Paper
Overcoming Occlusion with Inverse Graphics
Scene understanding tasks such as the prediction of object pose, shape, appearance and illumination are hampered by the occlusions often found in images. We propose a vision-as-inverse-graphics approach to han...
-
Chapter and Conference Paper
Efficient Continuous Relaxations for Dense CRF
Dense conditional random fields (CRF) with Gaussian pairwise potentials have emerged as a popular framework for several computer vision applications such as stereo correspondence and semantic segmentation. By ...
-
Chapter and Conference Paper
Faster and More Dynamic Maximum Flow by Incremental Breadth-First Search
We introduce the Excesses Incremental Breadth-First Search (Excesses IBFS) algorithm for maximum flow problems. We show that Excesses IBFS has the best overall practical performance on real-world instances, while...
-
Chapter and Conference Paper
Multi-utility Learning: Structured-Output Learning with Multiple Annotation-Specific Loss Functions
Structured-output learning is a challenging problem; particularly so because of the difficulty in obtaining large datasets of fully labelled instances for training. In this paper we try to overcome this diffic...
-
Chapter and Conference Paper
Perceptually Inspired Layout-Aware Losses for Image Segmentation
Interactive image segmentation is an important computer vision problem that has numerous real world applications. Models for image segmentation are generally trained to minimize the Hamming error in pixel labe...
-
Chapter and Conference Paper
A Contour Completion Model for Augmenting Surface Reconstructions
The availability of commodity depth sensors such as Kinect has enabled development of methods which can densely reconstruct arbitrary scenes. While the results of these methods are accurate and visually appeal...
-
Chapter and Conference Paper
Non-parametric Higher-Order Random Fields for Image Segmentation
Models defined using higher-order potentials are becoming increasingly popular in computer vision. However, the exact representation of a general higher-order potential defined over many variables is computati...
-
Chapter
Key Developments in Human Pose Estimation for Kinect
The last few years have seen a surge in the development of natural user interfaces. These interfaces do not require devices such as keyboards and mice that have been the dominant modes of interaction over the ...
-
Chapter and Conference Paper
Curvature Prior for MRF-Based Segmentation and Shape Inpainting
Most image labeling problems such as segmentation and image reconstruction are fundamentally ill-posed and suffer from ambiguities and noise. Higher-order image priors encode high-level structural dependencies...
-
Chapter and Conference Paper
Relating Things and Stuff by High-Order Potential Modeling
In the last few years, substantially different approaches have been adopted for segmenting and detecting “things” (object categories that have a well defined shape such as people and cars) and “stuff” (object ...
-
Chapter and Conference Paper
Learning to Efficiently Detect Repeatable Interest Points in Depth Data
Interest point (IP) detection is an important component of many computer vision methods. While there are a number of methods for detecting IPs in RGB images, modalities such as depth images and range scans hav...
-
Chapter and Conference Paper
Indoor Segmentation and Support Inference from RGBD Images
We present an approach to interpret the major surfaces, objects, and support relations of an indoor scene from an RGBD image. Most existing work ignores physical interactions or is applied only to tidy rooms a...
-
Chapter and Conference Paper
A Convex Discrete-Continuous Approach for Markov Random Fields
We propose an extension of the well-known LP relaxation for Markov random fields to explicitly allow continuous label spaces. Unlike conventional continuous formulations of labelling problems which assume that...
-
Chapter and Conference Paper
Large-Lexicon Attribute-Consistent Text Recognition in Natural Images
This paper proposes a new model for the task of word recognition in natural images that simultaneously models visual and lexicon consistency of words in a single probabilistic model. Our approach combines loca...
-
Chapter and Conference Paper
Latent Hough Transform for Object Detection
Hough transform based methods for object detection work by allowing image features to vote for the location of the object. While this representation allows for parts observed in different training instances to...
-
Chapter and Conference Paper
Putting MAP Back on the Map
Conditional Random Fields (CRFs) are popular models in computer vision for solving labeling problems such as image denoising. This paper tackles the rarely addressed but important problem of learning the full ...
-
Chapter and Conference Paper
Uncertainty Driven Multi-scale Optimization
This paper proposes a new multi-scale energy minimization algorithm which can be used to efficiently solve large scale labelling problems in computer vision. The basic modus operandi of any multi-scale method ...
-
Chapter and Conference Paper
Energy Minimization under Constraints on Label Counts
Many computer vision problems such as object segmentation or reconstruction can be formulated in terms of labeling a set of pixels or voxels. In certain scenarios, we may know the number of pixels or voxels wh...
