Related papers: Self-Supervised Learning of Motion Concepts by Opt…

A major challenge for video semantic segmentation is the lack of labeled data. In most benchmark datasets, only one frame of a video clip is annotated, which makes most supervised methods fail to utilize information from the rest of the…

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 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…

Ego-motion estimation is vital for drones when flying in GPS-denied environments. Vision-based methods struggle when flight speed increases and close-by objects lead to difficult visual conditions with considerable motion blur and large…

Unsupervised video object segmentation aims to detect the most salient object in a video without any external guidance regarding the object. Salient objects often exhibit distinctive movements compared to the background, and recent methods…

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…

In moving camera videos, motion segmentation is commonly performed using the image plane motion of pixels, or optical flow. However, objects that are at different depths from the camera can exhibit different optical flows even if they share…

In most of computer vision applications, motion blur is regarded as an undesirable artifact. However, it has been shown that motion blur in an image may have practical interests in fundamental computer vision problems. In this work, we…

Contrastive learning has shown great potential in video representation learning. However, existing approaches fail to sufficiently exploit short-term motion dynamics, which are crucial to various down-stream video understanding tasks. In…

Unsupervised multi-object segmentation has shown impressive results on images by utilizing powerful semantics learned from self-supervised pretraining. An additional modality such as depth or motion is often used to facilitate the…

Occlusion is an inevitable and critical problem in unsupervised optical flow learning. Existing methods either treat occlusions equally as non-occluded regions or simply remove them to avoid incorrectness. However, the occlusion regions can…

Imagining multiple consecutive frames given one single snapshot is challenging, since it is difficult to simultaneously predict diverse motions from a single image and faithfully generate novel frames without visual distortions. In this…

Optical flow estimation is one of the fundamental tasks in low-level computer vision, which describes the pixel-wise displacement and can be used in many other tasks. From the apparent aspect, the optical flow can be viewed as the…

Extracting physical dynamical system parameters from recorded observations is key in natural science. Current methods for automatic parameter estimation from video train supervised deep networks on large datasets. Such datasets require…

We address the problem of video representation learning without human-annotated labels. While previous efforts address the problem by designing novel self-supervised tasks using video data, the learned features are merely on a…

Unsupervised learning of optical flow, which leverages the supervision from view synthesis, has emerged as a promising alternative to supervised methods. However, the objective of unsupervised learning is likely to be unreliable in…

We present a self-supervised approach to estimate flow in camera image and top-view grid map sequences using fully convolutional neural networks in the domain of automated driving. We extend existing approaches for self-supervised optical…

One significant factor we expect the video representation learning to capture, especially in contrast with the image representation learning, is the object motion. However, we found that in the current mainstream video datasets, some action…

This paper introduces a novel method for self-supervised video representation learning via feature prediction. In contrast to the previous methods that focus on future feature prediction, we argue that a supervisory signal arising from…

Video super-resolution is currently one of the most active research topics in computer vision as it plays an important role in many visual applications. Generally, video super-resolution contains a significant component, i.e., motion…