Related papers: Optical Flow Dataset Synthesis from Unpaired Image…

The extremes of lighting (e.g. too much or too little light) usually cause many troubles for machine and human vision. Many recent works have mainly focused on under-exposure cases where images are often captured in low-light conditions…

Current methods for 2D and 3D object understanding struggle with severe occlusions in busy urban environments, partly due to the lack of large-scale labeled ground-truth annotations for learning occlusion. In this work, we introduce a novel…

The optical flow of natural scenes is a combination of the motion of the observer and the independent motion of objects. Existing algorithms typically focus on either recovering motion and structure under the assumption of a purely static…

Despite recent advances in text-to-image generation, using synthetically generated data seldom brings a significant boost in performance for supervised learning. Oftentimes, synthetic datasets do not faithfully recreate the data…

Automating quality inspection with computer vision techniques is often a very data-demanding task. Specifically, supervised deep learning requires a large amount of annotated images for training. In practice, collecting and annotating such…

Deep neural networks have been very successful in image estimation applications such as compressive-sensing and image restoration, as a means to estimate images from partial, blurry, or otherwise degraded measurements. These networks are…

Classical computation of optical flow involves generic priors (regularizers) that capture rudimentary statistics of images, but not long-range correlations or semantics. On the other hand, fully supervised methods learn the regularity in…

Recent diffusion models have exhibited great potential in generative modeling tasks. Part of their success can be attributed to the ability of training stable on huge sets of paired synthetic data. However, adapting these models to…

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…

Automatic document content processing is affected by artifacts caused by the shape of the paper, non-uniform and diverse color of lighting conditions. Fully-supervised methods on real data are impossible due to the large amount of data…

Most deep models for underwater image enhancement resort to training on synthetic datasets based on underwater image formation models. Although promising performances have been achieved, they are still limited by two problems: (1) existing…

Convolutional Neural Networks (CNN) have been found to have great potential in optical flow problems thanks to an abundance of data available for training a deep network. The displacement estimation step in UltraSound Elastography (USE) can…

To realize the full potential of deep learning for medical imaging, large annotated datasets are required for training. Such datasets are difficult to acquire because labeled medical images are not usually available due to privacy issues,…

Modern large displacement optical flow algorithms usually use an initialization by either sparse descriptor matching techniques or dense approximate nearest neighbor fields. While the latter have the advantage of being dense, they have the…

Recent scene text detection methods are almost based on deep learning and data-driven. Synthetic data is commonly adopted for pre-training due to expensive annotation cost. However, there are obvious domain discrepancies between synthetic…

Makeup transfer aims to apply the makeup style of a reference portrait to a source portrait while preserving identity and background. Early methods formulate this task as unsupervised image-to-image translation, relying on surrogate…

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…

Extracting information on fluid motion directly from images is challenging. Fluid flow represents a complex dynamic system governed by the Navier-Stokes equations. General optical flow methods are typically designed for rigid body motion,…

The state of the art in human-centric computer vision achieves high accuracy and robustness across a diverse range of tasks. The most effective models in this domain have billions of parameters, thus requiring extremely large datasets,…

The performance of learning-based denoising largely depends on clean supervision. However, it is difficult to obtain clean images in many scenes. On the contrary, the capture of multiple noisy frames for the same field of view is available…