This paper shows how to compute dense descriptors over images that can be used to augment ICP for localisation from large baselines.
[ICCV 2019 paper]
This paper shows how to solve simultaneous estimation of segmentation and motion estimation for events from a Neuromorphic (event) camera.
[ICCV 2019 paper]
This paper shows how to use Generative Adversarial Networks (GANs) to augment data for classes that are rare in the dataset. The expanded dataset can then be used to train a classifier that outperforms a classifier trained only on the original real images.
[MICCAI 2019 paper]
This paper shows how to address the diversity problem in Generative Adversarial Networks by introducing a loss that explicitly pulls the generated distribution towards the real distribution in a low dimensional latent space.
[CVPR 2019 paper]
This paper presents an approach to solving the hard problem of finding correspondences and localisation under extreme (180°) viewpoint variations. Depth estimation is used to filter key points for probable appearance in the opposing view and a robust descriptor is learned to aid matching.
[ICRA 2019 paper]
This paper shows how to use metric learning for active learning. In a metric space, examples of novel classes typically map to empty parts of the space. This can be detected automatically using the local ratio of unlabelled to labelled densities to select examples for active labelling.
[ICRA 2019 paper]
This paper shows the benefits of simultaneously estimating semantics and depth for a monocular image input stream. The resulting network can perform this estimate at 13ms per frame, enabling it to be used in real-time systems.
[ICRA 2019 paper]
This paper describes how to learn representations that transfer well between domains, while acknowledging that the target domain may have classes of data that are not present in the source domain.
[ICLR 2019 paper]
This paper shows how to compute camera motion using networks to estimate depth per frame and optical flow between frames with uncertainty. These estimates and uncertainties are then combined using conventional optimisation to obtain motion.
[ACCV 2018 paper]
This paper shows how to use a controller (based on decision ferns) to impose structure on the latent space of an autoencoder.
[ACCV 2018 paper]
This paper looks at how to measure the condition number of the training problem for deep networks, how this is affected by batch size and learning rate, and how this characterises performance in terms of convergence and generalisation.
[PAMI 2018 paper]
This paper shows how embedding a Gaussian kernel density classifier in latent space can be used to learn metric space representations of images. The learned representation transfers well to novel classes providing good clustering performance on this unseen data.
[ICIP 2018 paper]
This paper shows how to use a complex model to train a simpler one by applying a loss to cause the embeddings in latent space to converge. This accelerates depth estimation so that it can run at 30 frames per second on a TX2 for use in a VO/SLAM pipeline.
[IROS 2018 paper]
This paper shows how two robots that are exploring the same environment can share RGBD data to fill in gaps in each other's sensory data while simultaneously estimating their relative pose in the world.
[Sensors 2018 paper]
This paper introduces a method for very rapid sub-pixel refinement of correspondences. The method precomputes an update matrix that applies to the pixel intensity errors. The update matrix is itself computed from a quadratic and linear form of the pixels in the image patch. Finally the method also enables an estimation of the precision that will be obtained from a given reference patch.
[CVPR 2018 paper]