Related papers: UnFlow: Unsupervised Learning of Optical Flow with…

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…

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…

Self-supervised deep learning-based 3D scene understanding methods can overcome the difficulty of acquiring the densely labeled ground-truth and have made a lot of advances. However, occlusions and moving objects are still some of the major…

In the anomaly detection field, the scarcity of anomalous samples has directed the current research emphasis towards unsupervised anomaly detection. While these unsupervised anomaly detection methods offer convenience, they also overlook…

This paper studies unsupervised monocular depth prediction problem. Most of existing unsupervised depth prediction algorithms are developed for outdoor scenarios, while the depth prediction work in the indoor environment is still very…

Optical flow estimation is a fundamental problem of computer vision and has many applications in the fields of robot learning and autonomous driving. This paper reveals novel geometric laws of optical flow based on the insight and detailed…

To apply optical flow in practice, it is often necessary to resize the input to smaller dimensions in order to reduce computational costs. However, downsizing inputs makes the estimation more challenging because objects and motion ranges…

Optical flow is the motion of a pixel between at least two consecutive video frames and can be estimated through an end-to-end trainable convolutional neural network. To this end, large training datasets are required to improve the accuracy…

Denoising diffusion probabilistic models have transformed image generation with their impressive fidelity and diversity. We show that they also excel in estimating optical flow and monocular depth, surprisingly, without task-specific…

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…

Occlusions play an important role in disparity and optical flow estimation, since matching costs are not available in occluded areas and occlusions indicate depth or motion boundaries. Moreover, occlusions are relevant for motion…

Akin to many subareas of computer vision, the recent advances in deep learning have also significantly influenced the literature on optical flow. Previously, the literature had been dominated by classical energy-based models, which…

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…

Unsupervised optical flow estimators based on deep learning have attracted increasing attention due to the cost and difficulty of annotating for ground truth. Although performance measured by average End-Point Error (EPE) has improved over…

Estimating geometric elements such as depth, camera motion, and optical flow from images is an important part of the robot's visual perception. We use a joint self-supervised method to estimate the three geometric elements. Depth network,…

We propose GeoNet, a jointly unsupervised learning framework for monocular depth, optical flow and ego-motion estimation from videos. The three components are coupled by the nature of 3D scene geometry, jointly learned by our framework in…

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…

Optical flow estimation is a classical yet challenging task in computer vision. One of the essential factors in accurately predicting optical flow is to alleviate occlusions between frames. However, it is still a thorny problem for current…

This work presents DCFlow, a novel unsupervised cross-modal flow estimation framework that integrates a decoupled optimization strategy and a cross-modal consistency constraint. Unlike previous approaches that implicitly learn flow…

Monocular depth inference has gained tremendous attention from researchers in recent years and remains as a promising replacement for expensive time-of-flight sensors, but issues with scale acquisition and implementation overhead still…