Related papers: Occlusion Aware Unsupervised Learning of Optical F…

We introduce a way to learn to estimate a scene representation from a single image by predicting a low-dimensional subspace of optical flow for each training example, which encompasses the variety of possible camera and object movement.…

Optical flow estimation is crucial for various applications in vision and robotics. As the difficulty of collecting ground truth optical flow in real-world scenarios, most of the existing methods of learning optical flow still adopt…

Classical approaches for estimating optical flow have achieved rapid progress in the last decade. However, most of them are too slow to be applied in real-time video analysis. Due to the great success of deep learning, recent work has…

Modern optical flow methods are often composed of a cascade of many independent steps or formulated as a black box neural network that is hard to interpret and analyze. In this work we seek for a plain, interpretable, but learnable…

Synthetic datasets play a critical role in pre-training CNN models for optical flow, but they are painstaking to generate and hard to adapt to new applications. To automate the process, we present AutoFlow, a simple and effective method to…

In this work, we propose a method that combines unsupervised deep learning predictions for optical flow and monocular disparity with a model based optimization procedure for instantaneous camera pose. Given the flow and disparity…

This paper deals with the scarcity of data for training optical flow networks, highlighting the limitations of existing sources such as labeled synthetic datasets or unlabeled real videos. Specifically, we introduce a framework to generate…

Unsupervised learning from visual data is one of the most difficult challenges in computer vision, being a fundamental task for understanding how visual recognition works. From a practical point of view, learning from unsupervised visual…

Autonomous vehicle navigation is a key challenge in artificial intelligence, requiring robust and accurate decision-making processes. This research introduces a new end-to-end method that exploits multimodal information from a single…

While gait recognition has seen many advances in recent years, the occlusion problem has largely been ignored. This problem is especially important for gait recognition from uncontrolled outdoor sequences at range - since any small…

Although significant progress has been achieved on monocular maker-less human motion capture in recent years, it is still hard for state-of-the-art methods to obtain satisfactory results in occlusion scenarios. There are two main reasons:…

Image classification models, including convolutional neural networks (CNNs), perform well on a variety of classification tasks but struggle under conditions of partial occlusion, i.e., conditions in which objects are partially covered from…

Monocular depth inference has gained tremendous attention from researchers in recent years and remains as a promising replacement for expensive time-of-flight sensors, but issues with scale acquisition and implementation overhead still…

The application of machine learning in the study of phase transitions has achieved remarkable success in both equilibrium and non-equilibrium systems. It is widely recognized that unsupervised learning can retrieve phase transition…

We address unsupervised optical flow estimation for ego-centric motion. We argue that optical flow can be cast as a geometrical warping between two successive video frames and devise a deep architecture to estimate such transformation in…

We learn to compute optical flow by combining a classical spatial-pyramid formulation with deep learning. This estimates large motions in a coarse-to-fine approach by warping one image of a pair at each pyramid level by the current flow…

Unsupervised representation learning aims at finding methods that learn representations from data without annotation-based signals. Abstaining from annotations not only leads to economic benefits but may - and to some extent already does -…

CNN-based optical flow estimation has attracted attention recently, mainly due to its impressively high frame rates. These networks perform well on synthetic datasets, but they are still far behind the classical methods in real-world…

In this paper, we present a CNN-based fully unsupervised method for motion segmentation from optical flow. We assume that the input optical flow can be represented as a piecewise set of parametric motion models, typically, affine or…

The optical flow of humans is well known to be useful for the analysis of human action. Recent optical flow methods focus on training deep networks to approach the problem. However, the training data used by them does not cover the domain…