Related papers: OAS-Net: Occlusion Aware Sampling Network for Accu…

Deep Learning of neural networks has gained prominence in multiple life-critical applications like medical diagnoses and autonomous vehicle accident investigations. However, concerns about model transparency and biases persist. Explainable…

We present a framework to use recently introduced Capsule Networks for solving the problem of Optical Flow, one of the fundamental computer vision tasks. Most of the existing state of the art deep architectures either uses a correlation…

Two optical flow estimation problems are addressed: i) occlusion estimation and handling, and ii) estimation from image sequences longer than two frames. The proposed ContinualFlow method estimates occlusions before flow, avoiding the use…

This paper proposes a method for visually explaining the decision-making process of video recognition networks with a temporal extension of occlusion sensitivity analysis, called Adaptive Occlusion Sensitivity Analysis (AOSA). The key idea…

Deep learning approaches have achieved great success in addressing the problem of optical flow estimation. The keys to success lie in the use of cost volume and coarse-to-fine flow inference. However, the matching problem becomes ill-posed…

Occlusions pose a significant challenge to optical flow algorithms that rely on local evidences. We consider an occluded point to be one that is imaged in the first frame but not in the next, a slight overloading of the standard definition…

Existing recurrent optical flow estimation networks are computationally expensive since they use a fixed large number of iterations to update the flow field for each sample. An efficient network should skip iterations when the flow…

Optical flow estimation can be formulated as an end-to-end supervised learning problem, which yields estimates with a superior accuracy-runtime tradeoff compared to alternative methodology. In this paper, we make such networks estimate…

Significant progress has been made for estimating optical flow using deep neural networks. Advanced deep models achieve accurate flow estimation often with a considerable computation complexity and time-consuming training processes. In this…

Optical flow provides information on relative motion that is an important component in many computer vision pipelines. Neural networks provide high accuracy optical flow, yet their complexity is often prohibitive for application at the edge…

Panoramic images can broaden the Field of View (FoV), occlusion-aware prediction can deepen the understanding of the scene, and domain adaptation can transfer across viewing domains. In this work, we introduce a novel task, Occlusion-Aware…

The prediction of optical flow for occluded points is still a difficult problem that has not yet been solved. Recent methods use self-attention to find relevant non-occluded points as references for estimating the optical flow of occluded…

Scene flow represents the 3D motion of each point in the scene, which explicitly describes the distance and the direction of each point's movement. Scene flow estimation is used in various applications such as autonomous driving fields,…

The occlusion problem remains a crucial challenge in optical flow estimation (OFE). Despite the recent significant progress brought about by deep learning, most existing deep learning OFE methods still struggle to handle occlusions; in…

Using a layered representation for motion estimation has the advantage of being able to cope with discontinuities and occlusions. In this paper, we learn to estimate optical flow by combining a layered motion representation with deep…

Occlusions pose a significant challenge to optical flow algorithms that even rely on global evidences. We consider an occluded point to be one that is imaged in the reference frame but not in the next. Estimating the motion of these points…

Flow based garment warping is an integral part of image-based virtual try-on networks. However, optimizing a single flow predicting network for simultaneous global boundary alignment and local texture preservation results in sub-optimal…

Occlusion edge detection requires both accurate locations and context constraints of the contour. Existing CNN-based pipeline does not utilize adaptive methods to filter the noise introduced by low-level features. To address this dilemma,…

Recurrent neural networks are powerful tools for handling incomplete data problems in computer vision, thanks to their significant generative capabilities. However, the computational demand for these algorithms is too high to work in real…

State-of-the-art neural network models estimate large displacement optical flow in multi-resolution and use warping to propagate the estimation between two resolutions. Despite their impressive results, it is known that there are two…