Related papers: Evaluation of laser diffraction-based particle siz…
Accurate camera calibration is a fundamental task for 3D perception, especially when dealing with real-world, in-the-wild environments where complex optical distortions are common. Existing methods often rely on pre-rectified images or…
High angular resolution electron backscatter diffraction (HR-EBSD) affords an increase in angular resolution, as compared to 'conventional' Hough transform based EBSD, of two orders of magnitude, enabling measurements of relative…
Diffusion models have shown remarkable empirical success in sampling from rich multi-modal distributions. Their inference relies on numerically solving a certain differential equation. This differential equation cannot be solved in closed…
An experimental investigation of secondary atomization of spray in plain-jet airblast atomizers with a circular array of six liquid jets is studied. Crossflow of air with controlled velocity and pressure is applied to transverse jets. The…
We propose Diff-Instruct* (DI*), a data-efficient post-training approach for one-step text-to-image generative models to improve its human preferences without requiring image data. Our method frames alignment as online reinforcement…
We report a method to measure the size of single dielectric nanoparticles with high accuracy and precision using quantitative differential interference contrast (DIC) microscopy. Dielectric nanoparticles are detected optically by the…
Point supervision has become a scalable solution to address dense annotation for infrared small target detection, but its performance is limited by two coupled bottlenecks: unstable pseudo-label evolution in cluttered, low-contrast infrared…
Anatomical motion and deformation pose challenges to the understanding of the delivered dose distribution during radiotherapy treatments. Hence, deformable image registration (DIR) algorithms are increasingly used to map contours and dose…
We present the experimental phase function, degree of linear polarization (DLP), and linear depolarization (deltaL) curves of a set of forsterite samples representative of low-absorbing cosmic dust particles. The samples are prepared using…
X-ray fluorescence holography (XFH) is a method for obtaining diffraction-limited images of the local atomic structure around a given type of emitter. The reconstructed wave-field represents a distorted image of the scatterer electron…
Domain generalization (DG) for object detection aims to enhance detectors' performance in unseen scenarios. This task remains challenging due to complex variations in real-world applications. Recently, diffusion models have demonstrated…
We examine five machine learning-based architectures to estimate the droplet size distributions obtained using digital inline holography. The architectures, namely, U-Net, R2 U-Net, Attention U-Net, V-Net, and Residual U-Net are trained…
With the rapid advancement of diffusion models, a variety of fine-tuning methods have been developed, enabling high-fidelity image generation with high similarity to the target content using only 3 to 5 training images. More recently,…
LiDAR perception is severely limited by the distance-dependent sparsity of distant objects. While diffusion models can recover dense geometry, they suffer from prohibitive latency and physical hallucinations manifesting as ghost points. We…
The diffraction patterns of crystalline materials with local order contain sharp Bragg reflections as well as highly structured diffuse scattering. The instrumental requirements, experimental parameters and data processing techniques for…
The increasing scientific and technological interest in nanoparticles has raised the need for fast, efficient and precise characterization techniques. Powder diffraction is a very efficient experimental method, as it is straightforward and…
A dramatic influx of diffusion-generated images has marked recent years, posing unique challenges to current detection technologies. While the task of identifying these images falls under binary classification, a seemingly straightforward…
Diffusion distillation provides an effective approach for learning lightweight and few-steps diffusion models with efficient generation. However, evaluating their generalization remains challenging: theoretical metrics are often impractical…
Diffusion models have recently achieved remarkable performance in image super-resolution (SR), but their high computational cost limits practical deployment in remote sensing applications. To address this issue, we propose SlimDiffSR, a…
This Paper introduces a new Non-Contact, Optical method for displacement measurements, and strain mapping as well as comparing it to traditional Digital Image correlation (DIC) and laser interferometry measurement method. This Method…