Related papers: Predictive drift compensation of multi-frame STEM …
Modern camera pipelines apply extensive on-device processing, such as exposure adjustment, white balance, and color correction, which, while beneficial individually, often introduce photometric inconsistencies across views. These appearance…
We present an explicit-grid based method for efficiently reconstructing streaming radiance fields for novel view synthesis of real world dynamic scenes. Instead of training a single model that combines all the frames, we formulate the…
The vast majority of modern consumer-grade cameras employ a rolling shutter mechanism, leading to image distortions if the camera moves during image acquisition. In this paper, we present a novel deep network to solve the generic rolling…
The traditional techniques for extracting polycrystalline grain structures from microscopy images, such as transmission electron microscopy (TEM) and scanning electron microscopy (SEM), are labour-intensive, subjective, and time-consuming,…
In recent years, numerous real-time stereo matching methods have been introduced, but they often lack accuracy. These methods attempt to improve accuracy by introducing new modules or integrating traditional methods. However, the…
We introduce a novel Dual Input Stream Transformer (DIST) for the challenging problem of assigning fixation points from eye-tracking data collected during passage reading to the line of text that the reader was actually focused on. This…
Data in the real world often has an evolving distribution. Thus, machine learning models trained on such data get outdated over time. This phenomenon is called model drift. Knowledge of this drift serves two purposes: (i) Retain an accurate…
This research proposes a novel drift detection methodology for machine learning (ML) models based on the concept of ''deformation'' in the vector space representation of data. Recognizing that new data can act as forces stretching,…
Scanning transmission electron microscopy (STEM) is the most widespread adopted tool for atomic scale characterization of two-dimensional (2D) materials. Many 2D materials remain susceptible to electron beam damage, despite the standardized…
Forecasting a typical object's future motion is a critical task for interpreting and interacting with dynamic environments in computer vision. Event-based sensors, which could capture changes in the scene with exceptional temporal…
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…
Visual imitation learning methods demonstrate strong performance, yet they lack generalization when faced with visual input perturbations, including variations in lighting and textures, impeding their real-world application. We propose…
LiDAR-based semantic segmentation is a key component for autonomous mobile robots, yet large-scale annotation of LiDAR point clouds is prohibitively expensive and time-consuming. Although simulators can provide labeled synthetic data,…
The distance transform (DT) and its many variations are ubiquitous tools for image processing and analysis. In many imaging scenarios, the images of interest are corrupted by noise. This has a strong negative impact on the accuracy of the…
Moir\'e fringes are used throughout a wide variety of applications in physics and engineering to bring out small variations in an underlying lattice by comparing with another reference lattice. This method was recently demonstrated in…
Single-molecule localization microscopy techniques, like stochastic optical reconstruction microscopy (STORM), visualize biological specimens by stochastically exciting sparse blinking emitters. The raw images suffer from unwanted…
Progressive acquisition of slowly-scanned images is desirable for drift correction and real-time visualization. Interlacing methods are common approaches to storing and transmitting data on rectilinear grids, and here we propose using them…
The availability of precise and accurate simulation is a limiting factor for interpreting and forecasting data in many fields of science and engineering. Often, one or more distinct simulation software applications are developed, each with…
The use of fast pixelated detectors and direct electron detection technology is revolutionising many aspects of scanning transmission electron microscopy (STEM). The widespread adoption of these new technologies is impeded by the technical…
Due to the current lack of large-scale datasets at the million-scale level, tasks involving panoramic images predominantly rely on existing two-dimensional pre-trained image benchmark models as backbone networks. However, these networks are…