-
1
Learning to adapt for stereo
Published 2020“…Real world applications of stereo depth estimation require models that are robust to dynamic variations in the environment. …”
Conference item -
2
Domain-invariant stereo matching networks
Published 2020“…In this paper, we aim at designing a domain-invariant stereo matching network (DSMNet) that generalizes well to unseen scenes. …”
Conference item -
3
Joint optimization for object class segmentation and dense stereo reconstruction
Published 2011“…The problems of dense stereo reconstruction and object class segmentation can both be formulated as Random Field labeling problems, in which every pixel in the image is assigned a label corresponding to either its disparity, or an object class such as road or building. …”
Journal article -
4
Multiview stereo via volumetric graph-cuts and occlusion robust photo-consistency
Published 2007“…This paper presents a volumetric formulation for the multiview stereo problem which is amenable to a computationally tractable global optimization using Graph-cuts. …”
Journal article -
5
Efficient dense stereo with occlusions for new view-synthesis by four-state dynamic programming
Published 2006“…The new technique is based on an improved, dynamic-programming, stereo algorithm for efficient novel view generation. …”
Journal article -
6
Filter-based mean-field inference for random fields with higher-order terms and product label-spaces
Published 2012“…We demonstrate our techniques on joint stereo and object labeling problems, as well as object class segmentation, showing in addition for joint object-stereo labeling how our method provides an efficient approach to inference in product label-spaces. …”
Conference item -
7
Filter-based mean-field inference for random fields with higher-order terms and product label-spaces
Published 2014“…We demonstrate our techniques on joint stereo and object labelling problems, as well as object class segmentation, showing in addition for joint object-stereo labelling how our method provides an efficient approach to inference in product label-spaces. …”
Journal article -
8
Reconstructing relief surfaces
Published 2007“…This paper generalizes Markov Random Field (MRF) stereo methods to the generation of surface relief (height) fields rather than disparity or depth maps. …”
Journal article -
9
Incremental dense multi-modal 3D scene reconstruction
Published 2015“…Often, we use a combination of a stereo camera and lidar, however, process the acquired data in independent pipelines which generally leads to sub-optimal performance since both sensors suffer from different drawbacks. …”
Conference item -
10
A tiered move-making algorithm for general pairwise MRFs
Published 2012“…We evaluate the algorithm on many benchmark labeling problems such as stereo, image segmentation, image stitching and image denoising, as well as random energy minimization. …”
Conference item -
11
Dynamic hybrid algorithms for MAP inference in discrete MRFs
Published 2009“…We test the performance of our methods on energy functions encountered in the problems of stereo matching and color and object-based segmentation. …”
Journal article -
12
Efficient relaxations for dense CRFs with sparse higher-order potentials
Published 2019“…<p>Dense conditional random fields (CRFs) have become a popular framework for modelling several problems in computer vision such as stereo correspondence and multi-class semantic segmentation. …”
Journal article