Search Results for author:
Found 15 papers, 7 papers with code
DiverseNet: When One Right Answer is not Enough
For a single input, we learn to predict a range of possible answers.
Image Stylization for Robust Features
Local features that are robust to both viewpoint and appearance changes are crucial for many computer vision tasks.
Predicting Visual Overlap of Images Through Interpretable Non-Metric Box Embeddings
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
We propose that it is unnecessary to have such a high reliance on ground truth depths or even corresponding stereo pairs.
Footprints and Free Space from a Single Color Image
We introduce a model to predict the geometry of both visible and occluded traversable surfaces, given a single RGB image as input.
Self-Supervised Monocular Depth Hints
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.
Ranked #26 on
Monocular Depth Estimation
on KITTI Eigen split
Virtual Adversarial Ladder Networks For Semi-supervised Learning
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
We propose a simple method to construct a deep feature space, with explicitly disentangled representations of several known transformations.
Swipe Mosaics from Video
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.
Unsupervised Monocular Depth Estimation with Left-Right Consistency
Learning based methods have shown very promising results for the task of depth estimation in single images.
Ranked #3 on
Monocular Depth Estimation
on Mid-Air Dataset
Structured Prediction of Unobserved Voxels From a Single Depth Image
Building a complete 3D model of a scene, given only a single depth image, is underconstrained.
Hierarchical Subquery Evaluation for Active Learning on a Graph
Under some specific circumstances, Expected Error Reduction has been one of the strongest-performing informativeness criteria for active learning.
Becoming the Expert - Interactive Multi-Class Machine Teaching
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
Accurate semantic labeling of image pixels is difficult because intra-class variability is often greater than inter-class variability.
