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

Dataset distillation seeks to synthesize a highly compact dataset that achieves performance comparable to the original dataset on downstream tasks. For the classification task that use pre-trained self-supervised models as backbones,…

Event-based cameras have shown great promise in a variety of situations where frame based cameras suffer, such as high speed motions and high dynamic range scenes. However, developing algorithms for event measurements requires a new class…

Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training models to perform monocular depth estimation. In this paper, we…

The occlusion problem remains a crucial challenge in optical flow estimation (OFE). Despite the recent significant progress brought about by deep learning, most existing deep learning OFE methods still struggle to handle occlusions; in…

Concept drift is the phenomenon in which the underlying data distributions and statistical properties of a target domain change over time, leading to a degradation in model performance. Consequently, production models require continuous…

Event cameras such as DAVIS can simultaneously output high temporal resolution events and low frame-rate intensity images, which own great potential in capturing scene motion, such as optical flow estimation. Most of the existing optical…

Single view depth estimation models can be trained from video footage using a self-supervised end-to-end approach with view synthesis as the supervisory signal. This is achieved with a framework that predicts depth and camera motion, with a…

Scene flow is a challenging task aimed at jointly estimating the 3D structure and motion of the sensed environment. Although deep learning solutions achieve outstanding performance in terms of accuracy, these approaches divide the whole…

Deep convolutional neural networks (DCNN) have recently shown promising results in low-level computer vision problems such as optical flow and disparity estimation, but still, have much room to further improve their performance. In this…

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…

Time-dependent flow fields are typically generated by a computational fluid dynamics (CFD) method, which is an extremely time-consuming process. However, the latent relationship between the flow fields is governed by the Navier-Stokes…

Estimating depth from a single RGB images is a fundamental task in computer vision, which is most directly solved using supervised deep learning. In the field of unsupervised learning of depth from a single RGB image, depth is not given…

Optical flow estimation is an essential step for many real-world computer vision tasks. Existing deep networks have achieved satisfactory results by mostly employing a pyramidal coarse-to-fine paradigm, where a key process is to adopt…

Although multi-scale concepts have recently proven useful for recurrent network architectures in the field of optical flow and stereo, they have not been considered for image-based scene flow so far. Hence, based on a single-scale recurrent…

Existing rectified flow models are based on linear trajectories between data and noise distributions. This linearity enforces zero curvature, which can inadvertently force the image generation process through low-probability regions of the…

Assume you encounter an inverse problem that shall be solved for a large number of data, but no ground-truth data is available. To emulate this encounter, in this study, we assume it is unknown how to solve the imaging problem of Computed…

Deep learning approaches have achieved great success in addressing the problem of optical flow estimation. The keys to success lie in the use of cost volume and coarse-to-fine flow inference. However, the matching problem becomes ill-posed…

Traditional autonomous driving pipelines decouple camera design from downstream perception, relying on fixed optics and handcrafted ISPs that prioritize human viewable imagery rather than machine semantics. This separation discards…

Reconstructing high-quality magnetic resonance images (MRI) from undersampled raw data is of great interest from both technical and clinical point of views. To this date, however, it is still a mathematically and computationally challenging…

While many real-world data streams imply that they change frequently in a nonstationary way, most of deep learning methods optimize neural networks on training data, and this leads to severe performance degradation when dataset shift…