Related papers: NeuFlow: Real-time, High-accuracy Optical Flow Est…
Video super-resolution is currently one of the most active research topics in computer vision as it plays an important role in many visual applications. Generally, video super-resolution contains a significant component, i.e., motion…
To date, top-performing optical flow estimation methods only take pairs of consecutive frames into account. While elegant and appealing, the idea of using more than two frames has not yet produced state-of-the-art results. We present 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…
End-to-end trained convolutional neural networks have led to a breakthrough in optical flow estimation. The most recent advances focus on improving the optical flow estimation by improving the architecture and setting a new benchmark on the…
Miniature Micro Aerial Vehicles (MAV) are very suitable for flying in indoor environments, but autonomous navigation is challenging due to their strict hardware limitations. This paper presents a highly efficient computer vision algorithm…
In this work we propose a one-class self-supervised method for anomaly segmentation in images that benefits both from a modern machine learning approach and a more classic statistical detection theory. The method consists of four phases.…
Tracking the position and orientation of objects in space (i.e., in 6-DoF) in real time is a fundamental problem in robotics for environment interaction. It becomes more challenging when objects move at high-speed due to frame rate…
Reconstructing High Dynamic Range (HDR) video from image sequences captured with alternating exposures is challenging, especially in the presence of large camera or object motion. Existing methods typically align low dynamic range sequences…
Occlusions between consecutive frames have long posed a significant challenge in optical flow estimation. The inherent ambiguity introduced by occlusions directly violates the brightness constancy constraint and considerably hinders…
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…
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…
High-Q optical resonators allow label-free detection of individual nanoparticles through perturbation of optical signatures but have practical limitations due to reliance on random diffusion to deliver particles to the sensing region. We…
Self-supervised feed-forward methods for scene flow estimation offer real-time efficiency, but their supervision from two-frame point correspondences is unreliable and often breaks down under occlusions. Multi-frame supervision has the…
Gathering data and identifying events in various traffic situations remains an essential challenge for the systematic evaluation of a perception system's performance. Analyzing large-scale, typically unstructured, multi-modal, time series…
Optical flow, which expresses pixel displacement, is widely used in many computer vision tasks to provide pixel-level motion information. However, with the remarkable progress of the convolutional neural network, recent state-of-the-art…
In autonomous driving scenarios, the collected LiDAR point clouds can be challenged by occlusion and long-range sparsity, limiting the perception of autonomous driving systems. Scene completion methods can infer the missing parts of…
Human motion sensing plays a crucial role in smart systems for decision-making, user interaction, and personalized services. Extensive research that has been conducted is predominantly based on cameras, whose intrusive nature limits their…
3D scene flow estimation from point clouds is a low-level 3D motion perception task in computer vision. Flow embedding is a commonly used technique in scene flow estimation, and it encodes the point motion between two consecutive frames.…
Synthetic datasets play a critical role in pre-training CNN models for optical flow, but they are painstaking to generate and hard to adapt to new applications. To automate the process, we present AutoFlow, a simple and effective method to…
Event cameras capture brightness changes asynchronously with microsecond resolution, yet existing optical flow methods fail to fully exploit this temporal continuity. Frame-based approaches impose artificial accumulation latency and suffer…