Related papers: ViscNet: Vision-Based In-line Viscometry for Fluid…
Existing visual change detectors usually adopt CNNs or Transformers for feature representation learning and focus on learning effective representation for the changed regions between images. Although good performance can be obtained by…
Every volumetric velocimetry measurements based on tracer (particles, bubbles, etc.) detection can be strongly influenced by the optical screening phenomenon. It has to be taken into account when the the statistical properties associated to…
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…
Urban traffic management increasingly requires intelligent sensing systems capable of adapting to dynamic traffic conditions without costly infrastructure modifications. Vision-based vehicle detection has therefore become a key technology…
Today, video cameras are deployed in dense for monitoring physical places e.g., city, industrial, or agricultural sites. In the current systems, each camera node sends its feed to a cloud server individually. However, this approach suffers…
In this paper, we provide a novel dataset designed for camera invariant color constancy research. Camera invariance corresponds to the robustness of an algorithm's performance when run on images of the same scene taken by different cameras.…
Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining. However, they have not yet conquered the problem of image…
Contemporary approaches frame the color constancy problem as learning camera specific illuminant mappings. While high accuracy can be achieved on camera specific data, these models depend on camera spectral sensitivity and typically exhibit…
Monocular depth estimation is a crucial task in computer vision. While existing methods have shown impressive results under standard conditions, they often face challenges in reliably performing in scenarios such as low-light or rainy…
The history of computing started with analog computers consisting of physical devices performing specialized functions such as predicting the trajectory of cannon balls. In modern times, this idea has been extended, for example, to…
With advances in image recognition technology based on deep learning, automatic video analysis by Artificial Intelligence is becoming more widespread. As the amount of video used for image recognition increases, efficient compression…
We propose a self-supervised learning framework that uses unlabeled monocular video sequences to generate large-scale supervision for training a Visual Odometry (VO) frontend, a network which computes pointwise data associations across…
This paper presents VisMCA, an interactive visual analytics system that supports deepening understanding in ML results, augmenting users' capabilities in correcting misclassification, and providing an analysis of underlying patterns, in…
Event cameras respond to scene dynamics and offer advantages to estimate motion. Following recent image-based deep-learning achievements, optical flow estimation methods for event cameras have rushed to combine those image-based methods…
We propose a method to infer a dense depth map from a single image, its calibration, and the associated sparse point cloud. In order to leverage existing models (teachers) that produce putative depth maps, we propose an adaptive knowledge…
Lacunes of presumed vascular origin are fluid-filled cavities of between 3 - 15 mm in diameter, visible on T1 and FLAIR brain MRI. Quantification of lacunes relies on manual annotation or semi-automatic / interactive approaches; and almost…
Dataset distillation has demonstrated remarkable effectiveness in high-compression scenarios for image datasets. While video datasets inherently contain greater redundancy, existing video dataset distillation methods primarily focus on…
Imposing consistency through proxy tasks has been shown to enhance data-driven learning and enable self-supervision in various tasks. This paper introduces novel and effective consistency strategies for optical flow estimation, a problem…
Dynamic vision sensors or event cameras provide rich complementary information for video frame interpolation. Existing state-of-the-art methods follow the paradigm of combining both synthesis-based and warping networks. However, few of…
Accurate monocular depth estimation is crucial for 3D scene understanding, but existing methods often blur depth at object boundaries, introducing spurious intermediate 3D points. While achieving sharp edges usually requires very…