Related papers: BlinkVision: A Benchmark for Optical Flow, Scene F…
This paper presents an investigation into the estimation of optical and scene flow using RGBD information in scenarios where the RGB modality is affected by noise or captured in dark environments. Existing methods typically rely solely on…
Event-based vision, characterized by low redundancy, focus on dynamic motion, and inherent privacy-preserving properties, naturally fits the demands of video anomaly detection (VAD). However, the absence of dedicated event-stream anomaly…
Large Vision Language Models (LVLMs) achieve great performance on visual-language reasoning tasks, however, the black-box nature of LVLMs hinders in-depth research on the reasoning mechanism. As all images need to be converted into image…
Scene flow is a description of real world motion in 3D that contains more information than optical flow. Because of its complexity there exists no applicable variant for real-time scene flow estimation in an automotive or commercial vehicle…
In Brain-Computer Interface (BCI) research, the detailed study of blinks is crucial. They can be considered as noise, affecting the efficiency and accuracy of decoding users' cognitive states and intentions, or as potential features,…
We introduce AllTracker: a model that estimates long-range point tracks by way of estimating the flow field between a query frame and every other frame of a video. Unlike existing point tracking methods, our approach delivers…
Recently, Flow Matching models have pushed the boundaries of high-fidelity data generation across a wide range of domains. It typically employs a single large network to learn the entire generative trajectory from noise to data. Despite…
Point tracking aims to follow visual points through complex motion, occlusion, and viewpoint changes, and has advanced rapidly with modern foundation models. Yet progress toward general point tracking remains constrained by limited…
Simulating event streams from 3D scenes has become a common practice in event-based vision research, as it meets the demand for large-scale, high temporal frequency data without setting up expensive hardware devices or undertaking extensive…
RGB-Thermal (RGB-T) object tracking receives more and more attention due to the strongly complementary benefits of thermal information to visible data. However, RGB-T research is limited by lacking a comprehensive evaluation platform. In…
The performance of optical flow algorithms greatly depends on the specifics of the content and the application for which it is used. Existing and well established optical flow datasets are limited to rather particular contents from which…
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…
The paper addresses the shortcoming of current event-based vision (EBV) sensors in the context of particle imaging. Latency is introduced both on the pixel level as well as during read-out from the array and results in systemic timing…
Accurate perception of dynamic traffic scenes is crucial for high-level autonomous driving systems, requiring robust object motion estimation and instance segmentation. However, traditional methods often treat them as separate tasks,…
Over four decades, the majority addresses the problem of optical flow estimation using variational methods. With the advance of machine learning, some recent works have attempted to address the problem using convolutional neural network…
Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-called FlowNet was enabled by a large synthetically generated…
Today, people can easily record memorable moments, ranging from concerts, sports events, lectures, family gatherings, and birthday parties with multiple consumer cameras. However, synchronizing these cross-camera streams remains…
Scene flow estimation is the task of describing 3D motion between temporally successive observations. This thesis aims to build the foundation for building scene flow estimators with two important properties: they are scalable, i.e. they…
In autonomous driving community, numerous benchmarks have been established to assist the tasks of 3D/2D object detection, stereo vision, semantic/instance segmentation. However, the more meaningful dynamic evolution of the surrounding…
High-speed autonomous racing presents extreme perception challenges, including large relative velocities and substantial domain shifts from conventional urban-driving datasets. Existing benchmarks do not adequately capture these…