Related papers: Learning Optical Flow via Dilated Networks and Occ…

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…

The importance and demands of visual scene understanding have been steadily increasing along with the active development of autonomous systems. Consequently, there has been a large amount of research dedicated to semantic segmentation and…

Event cameras rely on motion to obtain information about scene appearance. This means that appearance and motion are inherently linked: either both are present and recorded in the event data, or neither is captured. Previous works treat the…

Recent works have shown that optical flow can be learned by deep networks from unlabelled image pairs based on brightness constancy assumption and smoothness prior. Current approaches additionally impose an augmentation regularization term…

In this paper, we propose a unified method to jointly learn optical flow and stereo matching. Our first intuition is stereo matching can be modeled as a special case of optical flow, and we can leverage 3D geometry behind stereoscopic…

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,…

Recently, with the advent of deep convolutional neural networks (DCNN), the improvements in visual saliency prediction research are impressive. One possible direction to approach the next improvement is to fully characterize the multi-scale…

Deblurring can not only provide visually more pleasant pictures and make photography more convenient, but also can improve the performance of objection detection as well as tracking. However, removing dynamic scene blur from images is a…

Many classical and learning-based optical flow methods rely on hierarchical concepts to improve both accuracy and robustness. However, one of the currently most successful approaches -- RAFT -- hardly exploits such concepts. In this work,…

Accurate routing network status estimation is a key component in Software Defined Networking. However, existing deep-learning-based methods for modeling network routing are not able to extrapolate towards unseen feature distributions. Nor…

Event camera has offered promising alternative for visual perception, especially in high speed and high dynamic range scenes. Recently, many deep learning methods have shown great success in providing promising solutions to many event-based…

Learning latent actions from large-scale videos is crucial for the pre-training of scalable embodied foundation models, yet existing methods often struggle with action-irrelevant distractors. Although incorporating action supervision can…

Disentangled representation learning aims to capture the underlying explanatory factors of observed data, enabling a principled understanding of the data-generating process. Recent advances in generative modeling have introduced new…

The difficulty of annotating training data is a major obstacle to using CNNs for low-level tasks in video. Synthetic data often does not generalize to real videos, while unsupervised methods require heuristic losses. Proxy tasks can…

Spiking Neural Networks (SNNs) are a promising research direction for building power-efficient information processing systems, especially for temporal tasks such as speech recognition. In SNNs, delays refer to the time needed for one spike…

Language models are prone to dataset biases, known as shortcuts and spurious correlations in data, which often result in performance drop on new data. We present a new debiasing framework called ``FairFlow'' that mitigates dataset biases by…

A prominent goal of representation learning research is to achieve representations which are factorized in a useful manner with respect to the ground truth factors of variation. The fields of disentangled and equivariant representation…

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…

Depth prediction plays a key role in understanding a 3D scene. Several techniques have been developed throughout the years, among which Convolutional Neural Network has recently achieved state-of-the-art performance on estimating depth from…

Video style transfer techniques inspire many exciting applications on mobile devices. However, their efficiency and stability are still far from satisfactory. To boost the transfer stability across frames, optical flow is widely adopted,…