Supervised training of optical flow predictors generally yields better accuracy than unsupervised training. However, the improved performance comes at an often high annotation cost. Semi-supervised training trades off accuracy against annotation cost. We use a simple yet effective semi-supervised training method to show that even a small fraction of labels can improve flow accuracy by a significant margin over unsupervised training. In addition, we propose active learning methods based on simple heuristics to further reduce the number of labels required to achieve the same target accuracy. Our experiments on both synthetic and real optical flow datasets show that our semi-supervised networks generally need around 50% of the labels to achiev...
Abstract. Assumptions of brightness constancy and spatial smoothness underlie most optical flow esti...
In this paper, two novel and practical regularizing methods are proposed to improve existing neural ...
Abstract—We present a supervised learning based method to estimate a per-pixel confidence for optica...
Imposing consistency through proxy tasks has been shown to enhance data-driven learning and enable s...
How important are training details and datasets to recent optical flow models like RAFT? And do they...
Recent work has shown that optical flow estimation can be formulated as a supervised learning proble...
Convolutional neural networks (CNNs) have recently been very successful in a variety of computer vis...
Learning-based optical flow estimation has been dominated with the pipeline of cost volume with conv...
none3noGGS Class 1 GGS Rating A++This paper deals with the scarcity of data for training optical...
We present DDFlow, a data distillation approach to learning optical flow estimation from unlabeled d...
In the era of end-to-end deep learning, many advances in computer vision are driven by large amounts...
International audienceIn the last few years there has been a growing interest in approaches that all...
Optical flow estimation is a fundamental and ill-posed problem in computer vision. To recover a dens...
International audienceState-of-the-art methods for optical flow estimation rely on deep learning, wh...
none3noThis paper proposes a framework to guide an optical flow network with external cues to achiev...
Abstract. Assumptions of brightness constancy and spatial smoothness underlie most optical flow esti...
In this paper, two novel and practical regularizing methods are proposed to improve existing neural ...
Abstract—We present a supervised learning based method to estimate a per-pixel confidence for optica...
Imposing consistency through proxy tasks has been shown to enhance data-driven learning and enable s...
How important are training details and datasets to recent optical flow models like RAFT? And do they...
Recent work has shown that optical flow estimation can be formulated as a supervised learning proble...
Convolutional neural networks (CNNs) have recently been very successful in a variety of computer vis...
Learning-based optical flow estimation has been dominated with the pipeline of cost volume with conv...
none3noGGS Class 1 GGS Rating A++This paper deals with the scarcity of data for training optical...
We present DDFlow, a data distillation approach to learning optical flow estimation from unlabeled d...
In the era of end-to-end deep learning, many advances in computer vision are driven by large amounts...
International audienceIn the last few years there has been a growing interest in approaches that all...
Optical flow estimation is a fundamental and ill-posed problem in computer vision. To recover a dens...
International audienceState-of-the-art methods for optical flow estimation rely on deep learning, wh...
none3noThis paper proposes a framework to guide an optical flow network with external cues to achiev...
Abstract. Assumptions of brightness constancy and spatial smoothness underlie most optical flow esti...
In this paper, two novel and practical regularizing methods are proposed to improve existing neural ...
Abstract—We present a supervised learning based method to estimate a per-pixel confidence for optica...