Related papers: Orientation-Adaptive Virtual Imaging of Defects us…
This paper aims to address the unsupervised video anomaly detection (VAD) problem, which involves classifying each frame in a video as normal or abnormal, without any access to labels. To accomplish this, the proposed method employs…
In the technique of Electron Backscatter Diffraction (EBSD), the accurate detection and identification of different phases existing in a sample is often limited by overlapping Kikuchi diffraction patterns originating from the extended…
Monocular omnidirectional visual odometry (OVO) systems leverage 360-degree cameras to overcome field-of-view limitations of perspective VO systems. However, existing methods, reliant on handcrafted features or photometric objectives, often…
The stylization of 3D scenes is an increasingly attractive topic in 3D vision. Although image style transfer has been extensively researched with promising results, directly applying 2D style transfer methods to 3D scenes often fails to…
The routine and unique determination of minor phases in microstructures is critical to materials science. In metallurgy alone, applications include alloy and process development and the understanding of degradation in service. We develop a…
Erase inpainting, or object removal, aims to precisely remove target objects within masked regions while preserving the overall consistency of the surrounding content. Despite diffusion-based methods have made significant strides in the…
Video anomaly detection (VAD) is a vital yet complex open-set task in computer vision, commonly tackled through reconstruction-based methods. However, these methods struggle with two key limitations: (1) insufficient robustness in open-set…
Out-of-distribution (OOD) detection is a critical task in machine learning, particularly for safety-critical applications where unexpected inputs must be reliably flagged. While hierarchical variational autoencoders (HVAEs) offer improved…
Ghost imaging leverages a single-pixel detector with no spatial resolution to acquire object echo intensity signals, which are correlated with illumination patterns to reconstruct an image. This architecture inherently mitigates scattering…
Use of electron vortex beams (EVB), that is convergent electron beams carrying an orbital angular momentum (OAM), is a novel development in the field of transmission electron microscopy. They should allow measurement of element-specific…
Regression loss design is an essential topic for oriented object detection. Due to the periodicity of the angle and the ambiguity of width and height definition, traditional L1-distance loss and its variants have been suffered from the…
Diffusion models excel at generation, but their latent spaces are high dimensional and not explicitly organized for interpretation or control. We introduce ConDA (Contrastive Diffusion Alignment), a plug-and-play geometry layer that applies…
Omnidirectional applications are immersive and highly interactive, which can improve the efficiency of remote collaborative work among factory workers. The transmission of omnidirectional video (OV) is the most important step in…
Slot Attention (SA) with pretrained diffusion models has recently shown promise for object-centric learning (OCL), but suffers from slot entanglement and weak alignment between object slots and image content. We propose Contrastive…
High-contrast imaging and spectroscopy provide unique constraints for exoplanet formation models as well as for planetary atmosphere models. Instrumentation techniques in this field have greatly improved over the last two decades, with the…
Existing approaches to drone visual geo-localization predominantly adopt the image-based setting, where a single drone-view snapshot is matched with images from other platforms. Such task formulation, however, underutilizes the inherent…
Due to its extensive applications, aerial image object detection has long been a hot topic in computer vision. In recent years, advancements in Unmanned Aerial Vehicles (UAV) technology have further propelled this field to new heights,…
The past decade has witnessed significant progress on detecting objects in aerial images that are often distributed with large scale variations and arbitrary orientations. However most of existing methods rely on heuristically defined…
Four-dimensional Digital Subtraction Angiography (4D DSA) is a medical imaging technique that provides a series of 2D images captured at different stages and angles during the process of contrast agent filling blood vessels. It plays a…
Estimating relative pose from image pairs fundamentally requires only a minimal subset of geometrically consistent correspondences. However, most learning-based approaches rely on dense matching or direct regression, leading to redundancy…