Related papers: Occlusion Aware Unsupervised Learning of Optical F…

We propose a novel method for learning convolutional neural image representations without manual supervision. We use motion cues in the form of optical flow, to supervise representations of static images. The obvious approach of training a…

Imposing consistency through proxy tasks has been shown to enhance data-driven learning and enable self-supervision in various tasks. This paper introduces novel and effective consistency strategies for optical flow estimation, a problem…

Optical flow estimation is a fundamental problem in computer vision, yet the reliance on expensive ground-truth annotations limits the scalability of supervised approaches. Although unsupervised and semi-supervised methods alleviate this…

We present DistillFlow, a knowledge distillation approach to learning optical flow. DistillFlow trains multiple teacher models and a student model, where challenging transformations are applied to the input of the student model to generate…

We study the unsupervised learning of CNNs for optical flow estimation using proxy ground truth data. Supervised CNNs, due to their immense learning capacity, have shown superior performance on a range of computer vision problems including…

Depth estimation is a fundamental issue in 4-D light field processing and analysis. Although recent supervised learning-based light field depth estimation methods have significantly improved the accuracy and efficiency of traditional…

The scarcity of ground-truth labels poses one major challenge in developing optical flow estimation models that are both generalizable and robust. While current methods rely on data augmentation, they have yet to fully exploit the rich…

Estimating motion in videos is an essential computer vision problem with many downstream applications, including controllable video generation and robotics. Current solutions are primarily trained using synthetic data or require tuning of…

Unsupervised optical flow methods typically lack reliable uncertainty estimation, limiting their robustness and interpretability. We propose U$^{2}$Flow, the first recurrent unsupervised framework that jointly estimates optical flow and…

Optical flow is an indispensable building block for various important computer vision tasks, including motion estimation, object tracking, and disparity measurement. In this work, we propose TransFlow, a pure transformer architecture for…

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…

Learning with neural networks from a continuous stream of visual information presents several challenges due to the non-i.i.d. nature of the data. However, it also offers novel opportunities to develop representations that are consistent…

Existing optical flow methods are erroneous in challenging scenes, such as fog, rain, and night because the basic optical flow assumptions such as brightness and gradient constancy are broken. To address this problem, we present an…

Learning-based perception and prediction modules in modern autonomous driving systems typically rely on expensive human annotation and are designed to perceive only a handful of predefined object categories. This closed-set paradigm is…

Most of current Convolution Neural Network (CNN) based methods for optical flow estimation focus on learning optical flow on synthetic datasets with groundtruth, which is not practical. In this paper, we propose an unsupervised optical flow…

Self-supervised monocular depth estimation, aiming to learn scene depths from single images in a self-supervised manner, has received much attention recently. In spite of recent efforts in this field, how to learn accurate scene depths and…

3D scene flow estimation is a vital tool in perceiving our environment given depth or range sensors. Unlike optical flow, the data is usually sparse and in most cases partially occluded in between two temporal samplings. Here we propose a…

(Very early draft)Traditional supervised learning keeps pushing convolution neural network(CNN) achieving state-of-art performance. However, lack of large-scale annotation data is always a big problem due to the high cost of it, even…

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…

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…