Search Results for author: Gabriel J. Brostow

Found 15 papers, 7 papers with code

Image Stylization for Robust Features

no code implementations16 Aug 2020 Iaroslav Melekhov, Gabriel J. Brostow, Juho Kannala, Daniyar Turmukhambetov

Local features that are robust to both viewpoint and appearance changes are crucial for many computer vision tasks.

Autonomous Driving Image Stylization +1

Predicting Visual Overlap of Images Through Interpretable Non-Metric Box Embeddings

1 code implementation ECCV 2020 Anita Rau, Guillermo Garcia-Hernando, Danail Stoyanov, Gabriel J. Brostow, Daniyar Turmukhambetov

Even when this is a known scene, the answer typically requires an expensive search across scale space, with matching and geometric verification of large sets of local features.

Learning Stereo from Single Images

2 code implementations ECCV 2020 Jamie Watson, Oisin Mac Aodha, Daniyar Turmukhambetov, Gabriel J. Brostow, Michael Firman

We propose that it is unnecessary to have such a high reliance on ground truth depths or even corresponding stereo pairs.

Monocular Depth Estimation Stereo Matching

Footprints and Free Space from a Single Color Image

1 code implementation CVPR 2020 Jamie Watson, Michael Firman, Aron Monszpart, Gabriel J. Brostow

We introduce a model to predict the geometry of both visible and occluded traversable surfaces, given a single RGB image as input.

Semantic Segmentation

Self-Supervised Monocular Depth Hints

1 code implementation ICCV 2019 Jamie Watson, Michael Firman, Gabriel J. Brostow, Daniyar Turmukhambetov

Monocular depth estimators can be trained with various forms of self-supervision from binocular-stereo data to circumvent the need for high-quality laser scans or other ground-truth data.

Depth Prediction Monocular Depth Estimation +1

Virtual Adversarial Ladder Networks For Semi-supervised Learning

2 code implementations20 Nov 2017 Saki Shinoda, Daniel E. Worrall, Gabriel J. Brostow

Semi-supervised learning (SSL) partially circumvents the high cost of labeling data by augmenting a small labeled dataset with a large and relatively cheap unlabeled dataset drawn from the same distribution.

Interpretable Transformations with Encoder-Decoder Networks

no code implementations ICCV 2017 Daniel E. Worrall, Stephan J. Garbin, Daniyar Turmukhambetov, Gabriel J. Brostow

We propose a simple method to construct a deep feature space, with explicitly disentangled representations of several known transformations.

Swipe Mosaics from Video

no code implementations26 Sep 2016 Malcolm Reynolds, Tom S. F. Haines, Gabriel J. Brostow

We propose Swipe Mosaics, an interactive visualization that places the individual video frames on a 2D planar map that represents the layout of the physical scene.

Visual Odometry

Hierarchical Subquery Evaluation for Active Learning on a Graph

no code implementations CVPR 2014 Oisin Mac Aodha, Neill D. F. Campbell, Jan Kautz, Gabriel J. Brostow

Under some specific circumstances, Expected Error Reduction has been one of the strongest-performing informativeness criteria for active learning.

Active Learning graph construction +1

Becoming the Expert - Interactive Multi-Class Machine Teaching

no code implementations CVPR 2015 Edward Johns, Oisin Mac Aodha, Gabriel J. Brostow

However, image-importance is individual-specific, i. e. a teaching image is important to a student if it changes their overall ability to discriminate between classes.

Context Tricks for Cheap Semantic Segmentation

no code implementations17 Feb 2015 Thanapong Intharah, Gabriel J. Brostow

Accurate semantic labeling of image pixels is difficult because intra-class variability is often greater than inter-class variability.

Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.