Related papers: Segmenting the Complex and Irregular in Two-Phase …
Understanding the three-dimensional motion of bubbles is essential for interpreting transport and mixing in multiphase flows, especially when bubbles deform under shear or move rapidly through the flow field. In many laboratory setups, only…
We developed a computer vision-based methodology to achieve precise 3D segmentation and tracking of superbubbles within magnetohydrodynamic simulations of the supernova-driven interstellar medium. Leveraging advanced 3D transformer models,…
We investigate a two-dimensional network simulator that model the dynamics of two-phase immiscible bulk flow where film flow can be neglected. We present a method for simulating the detailed dynamical process where the two phases are…
Fragmentation of bubbles and droplets in turbulence produces a dispersed phase spanning a broad range of scales, encompassing everything from droplets in nanoemulsions to centimeter-sized bubbles entrained in breaking waves. Along with…
Aiming to predict the complete shapes of partially occluded objects, amodal segmentation is an important step towards visual intelligence. With crucial significance, practical prior knowledge derives from sufficient training, while limited…
High-speed video (HSV) segmentation is essential for analyzing dynamic physical processes in scientific and industrial applications, such as boiling heat transfer. Existing models like U-Net struggle with generalization and accurately…
Optical Flow Estimation aims to find the 2D dense motion field between two frames. Due to the limitation of model structures and training datasets, existing methods often rely too much on local clues and ignore the integrity of objects,…
We present Segment Anything Model 2 (SAM 2), a foundation model towards solving promptable visual segmentation in images and videos. We build a data engine, which improves model and data via user interaction, to collect the largest video…
This work uncovers the low-dimensional nature the complex dynamics of actuated separated flows. Namely, motivated by the problem of model-based predictive control of separated flows, we identify the requirements on a model-based observer…
Various biological and chemical processes lead to the nucleation and growth of non-wetting fluid bubbles within the pore space of a granular medium, such as the formation of gas bubbles in liquid-saturated lake-bed sediments. In…
Segmented light field images can serve as a powerful representation in many of computer vision tasks exploiting geometry and appearance of objects, such as object pose tracking. In the light field domain, segmentation presents an additional…
Segmentation is vital for ophthalmology image analysis. But its various modal images hinder most of the existing segmentation algorithms applications, as they rely on training based on a large number of labels or hold weak generalization…
Amodal segmentation is a challenging task that aims to predict the complete geometric shape of objects, including their occluded regions. Although existing methods primarily focus on amodal segmentation within the training domain, these…
An increasing number of research topics and applications ask for a precise measurement of the size distribution of small bubbles in a liquid - and hence for reliable and automated image analysis. However, due to the strong mismatch between…
Fundamental models, trained on large-scale datasets and adapted to new data using innovative learning methods, have revolutionized various fields. In materials science, microstructure image segmentation plays a pivotal role in understanding…
Segmentation remains an important problem in image processing. For homogeneous (piecewise smooth) images, a number of important models have been developed and refined over the past several decades. However, these models often fail when…
The objective of this paper is motion segmentation -- discovering and segmenting the moving objects in a video. This is a much studied area with numerous careful, and sometimes complex, approaches and training schemes including:…
Knowledge of bubble and drop size distributions in two-phase flows is important for characterizing a wide range of phenomena, including combustor ignition, sonar communication, and cloud formation. The physical mechanisms driving the…
The Segment Anything Model (SAM), developed by Meta AI Research, represents a significant breakthrough in computer vision, offering a robust framework for image and video segmentation. This survey provides a comprehensive exploration of the…
Improved understanding of gas/liquid transport in electrochemical gas-evolving systems is increasingly demanded for optimizing device performance. However, high-resolution measurement techniques for in-situ imaging remain limited. This work…