Related papers: FAST: Foreground-aware Diffusion with Accelerated …
Normalizing flows are tractable density models that can approximate complicated target distributions, e.g. Boltzmann distributions of physical systems. However, current methods for training flows either suffer from mode-seeking behavior,…
Subsampling is commonly used to mitigate costs associated with data acquisition, such as time or energy requirements, motivating the development of algorithms for estimating the fully-sampled signal of interest $x$ from partially observed…
Automated f ault detection and monitoring in engineering are critical but frequently difficult owing to the necessity for collecting and labeling large amounts of defective samples . We present an unsupervised method that uses the high end…
In contemporary society, surveillance anomaly detection, i.e., spotting anomalous events such as crimes or accidents in surveillance videos, is a critical task. As anomalies occur rarely, most training data consists of unlabeled videos…
Diffusion models have demonstrated remarkable success in generative tasks, yet their iterative denoising process results in slow inference, limiting their practicality. While existing acceleration methods exploit the well-known U-shaped…
Foreground segmentation is a fundamental task in computer vision, encompassing various subdivision tasks. Previous research has typically designed task-specific architectures for each task, leading to a lack of unification. Moreover, they…
Photoacoustic imaging (PAI) is an emerging medical imaging modality capable of providing high spatial resolution of Ultrasound (US) imaging and high contrast of optical imaging. Delay-and-Sum (DAS) is the most common beamforming algorithm…
Delineating farmland boundaries is essential for agricultural management such as crop monitoring and agricultural census. Traditional methods using remote sensing imagery have been efficient but limited in generalisation. The Segment…
Reconstruction-based approaches have achieved remarkable outcomes in anomaly detection. The exceptional image reconstruction capabilities of recently popular diffusion models have sparked research efforts to utilize them for enhanced…
Recent advances in diffusion models have enabled the creation of deceptively real images, posing significant security risks when misused. In this study, we empirically show that different timesteps of DDIM inversion reveal varying subtle…
Diffusion models provide a powerful way to incorporate complex prior information for solving inverse problems. However, existing methods struggle to correctly incorporate guidance from conflicting signals in the prior and measurement, and…
Diffusion models have garnered significant interest from the community for their great generative ability across various applications. However, their typical multi-step sequential-denoising nature gives rise to high cumulative latency,…
Anomaly detection is a critical task in industrial manufacturing, aiming to identify defective parts of products. Most industrial anomaly detection methods assume the availability of sufficient normal data for training. This assumption may…
Face anti-spoofing (FAS) plays a critical role in securing face recognition systems from different presentation attacks. Previous works leverage auxiliary pixel-level supervision and domain generalization approaches to address unseen spoof…
Fluid antenna systems (FAS) offer enhanced spatial diversity for next-generation wireless systems. However, acquiring accurate channel state information (CSI) remains challenging due to the large number of reconfigurable ports and the…
Anomaly detection plays a vital role in industrial manufacturing. Due to the scarcity of real defect images, unsupervised approaches that rely solely on normal images have been extensively studied. Recently, diffusion-based generative…
Dense random sampling and surfacing of shapes encoded via implicit occupancy functions (OFs) are critical elements of many applications. Existing methods largely provide either one or the other of random sampling or mesh surfaces: ray…
We present an approach for improving spatial frequency sampling in active incoherent millimeter-wave (AIM) imaging systems using frequency diversity. AIM imaging relies on active transmission of spatio-temporally incoherent signals to…
In order to navigate safely and reliably in off-road and unstructured environments, robots must detect anomalies that are out-of-distribution (OOD) with respect to the training data. We present an analysis-by-synthesis approach for…
Artistic style transfer aims to transfer the learned artistic style onto an arbitrary content image, generating artistic stylized images. Existing generative adversarial network-based methods fail to generate highly realistic stylized…