Related papers: Beyond Reconstruction: Reconstruction-to-Vector Di…
Due to scarcity of anomaly situations in the early manufacturing stage, an unsupervised anomaly detection (UAD) approach is widely adopted which only uses normal samples for training. This approach is based on the assumption that the…
Recent Text-to-Video (T2V) models have demonstrated powerful capability in visual simulation of real-world geometry and physical laws, indicating its potential as implicit world models. Inspired by this, we explore the feasibility of…
Image downscaling is critical for efficient storage and transmission of high-resolution (HR) images. Existing learning-based methods focus on performing downscaling within the sRGB domain, which typically suffers from blurred details and…
Neural networks follow a gradient-based learning scheme, adapting their mapping parameters by back-propagating the output loss. Samples unlike the ones seen during training cause a different gradient distribution. Based on this intuition,…
Millimeter-wave radar enables robust environment perception in autonomous systems under adverse conditions yet suffers from sparse, noisy point clouds with low angular resolution. Existing diffusion-based radar enhancement methods either…
Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences where motion causes significant geometric ambiguity. To address…
Improving the quality of hyperspectral images (HSIs), such as through super-resolution, is a crucial research area. However, generative modeling for HSIs presents several challenges. Due to their high spectral dimensionality, HSIs are too…
Anomaly detection (AD) has been extensively studied and applied in a wide range of scenarios in the recent past. However, there are still gaps between achieved and desirable levels of recognition accuracy for making AD for practical…
In the visual generative area, discrete diffusion models are gaining traction for their efficiency and compatibility. However, pioneered attempts still fall behind their continuous counterparts, which we attribute to noise (absorbing state)…
Anomaly detection has a wide range of applications and is especially important in industrial quality inspection. Currently, many top-performing anomaly-detection models rely on feature-embedding methods. However, these methods do not…
Few-Shot Industrial Visual Anomaly Detection (FS-IVAD) comprises a critical task in modern manufacturing settings, where automated product inspection systems need to identify rare defects using only a handful of normal/defect-free training…
Video Anomaly Detection (VAD) is essential for computer vision research. Existing VAD methods utilize either reconstruction-based or prediction-based frameworks. The former excels at detecting irregular patterns or structures, whereas the…
Unsupervised visual anomaly detection from multi-view images presents a significant challenge: distinguishing genuine defects from benign appearance variations caused by viewpoint changes. Existing methods, often designed for single-view…
In the realm of 3D reconstruction from 2D images, a persisting challenge is to achieve high-precision reconstructions devoid of 3D Ground Truth data reliance. We present UNeR3D, a pioneering unsupervised methodology that sets a new standard…
Unsupervised anomaly detection (UAD) based on deep generative modelling has been increasingly explored for identifying pathological brain abnormalities without requiring voxel-level annotations. By learning the distribution of healthy…
This paper investigates the performance of diffusion models for video anomaly detection (VAD) within the most challenging but also the most operational scenario in which the data annotations are not used. As being sparse, diverse,…
Low-field to high-field MRI synthesis has emerged as a cost-effective strategy to enhance image quality under hardware and acquisition constraints, particularly in scenarios where access to high-field scanners is limited or impractical.…
Reference-guided image generation has progressed rapidly, yet current diffusion models still struggle to preserve fine-grained visual details when refining a generated image using a reference. This limitation arises because VAE-based latent…
Out-of-distribution (OOD) detection is crucial for enhancing the generalization of AI models used in mammogram screening. Given the challenge of limited prior knowledge about OOD samples in external datasets, unsupervised generative…
Does the intrinsic curvature of complex networks hold the key to unveiling graph anomalies that conventional approaches overlook? Reconstruction-based graph anomaly detection (GAD) methods overlook such geometric outliers, focusing only on…