Related papers: Unsupervised Learning of Dense Optical Flow, Depth…
Event-based cameras have recently shown great potential for high-speed motion estimation owing to their ability to capture temporally rich information asynchronously. Spiking Neural Networks (SNNs), with their neuro-inspired event-driven…
We propose a novel approach for optical flow estimation , targeted at large displacements with significant oc-clusions. It consists of two steps: i) dense matching by edge-preserving interpolation from a sparse set of matches; ii)…
In the current monocular depth research, the dominant approach is to employ unsupervised training on large datasets, driven by warped photometric consistency. Such approaches lack robustness and are unable to generalize to challenging…
The task of blood vessel segmentation in microscopy images is crucial for many diagnostic and research applications. However, vessels can look vastly different, depending on the transient imaging conditions, and collecting data for…
Unsupervised monocular depth and ego-motion estimation has drawn extensive research attention in recent years. Although current methods have reached a high up-to-scale accuracy, they usually fail to learn the true scale metric due to the…
In the context of managing distributed energy resources (DERs) within distribution networks (DNs), this work focuses on the task of developing local controllers. We propose an unsupervised learning framework to train functions that can…
Depth completion, the technique of estimating a dense depth image from sparse depth measurements, has a variety of applications in robotics and autonomous driving. However, depth completion faces 3 main challenges: the irregularly spaced…
Deep learning has revolutionized the field of computer vision by introducing large scale neural networks with millions of parameters. Training these networks requires massive datasets and leads to intransparent models that can fail to…
A significant weakness of most current deep Convolutional Neural Networks is the need to train them using vast amounts of manu- ally labelled data. In this work we propose a unsupervised framework to learn a deep convolutional neural…
We address unsupervised optical flow estimation for ego-centric motion. We argue that optical flow can be cast as a geometrical warping between two successive video frames and devise a deep architecture to estimate such transformation in…
Unsupervised monocular depth estimation has received widespread attention because of its capability to train without ground truth. In real-world scenarios, the images may be blurry or noisy due to the influence of weather conditions and…
Current computer vision tasks based on deep learning require a huge amount of data with annotations for model training or testing, especially in some dense estimation tasks, such as optical flow segmentation and depth estimation. In…
EEG-based emotion recognition often requires sufficient labeled training samples to build an effective computational model. Labeling EEG data, on the other hand, is often expensive and time-consuming. To tackle this problem and reduce the…
Egocentric gesture recognition is a pivotal technology for enhancing natural human-computer interaction, yet traditional RGB-based solutions suffer from motion blur and illumination variations in dynamic scenarios. While event cameras show…
Optical flow computation with frame-based cameras provides high accuracy but the speed is limited either by the model size of the algorithm or by the frame rate of the camera. This makes it inadequate for high-speed applications. Event…
Learning-based, single-view depth estimation often generalizes poorly to unseen datasets. While learning-based, two-frame depth estimation solves this problem to some extent by learning to match features across frames, it performs poorly at…
Event-based motion field estimation is an important task. However, current optical flow methods face challenges: learning-based approaches, often frame-based and relying on CNNs, lack cross-domain transferability, while model-based methods,…
Optical flow estimation is a crucial subfield of computer vision, serving as a foundation for video tasks. However, the real-world robustness is limited by animated synthetic datasets for training. This introduces domain gaps when applied…
While learning based depth estimation from images/videos has achieved substantial progress, there still exist intrinsic limitations. Supervised methods are limited by a small amount of ground truth or labeled data and unsupervised methods…
Image-based depth estimation has gained significant attention in recent research on computer vision for autonomous vehicles in intelligent transportation systems. This focus stems from its cost-effectiveness and wide range of potential…