Related papers: SGANet: Semantic and Geometric Alignment for Multi…

The inability of state-of-the-art semantic segmentation methods to detect anomaly instances hinders them from being deployed in safety-critical and complex applications, such as autonomous driving. Recent approaches have focused on either…

Comparing two images in a view-invariant way has been a challenging problem in computer vision for a long time, as visual features are not stable under large view point changes. In this paper, given a single input image of an object, we…

Monocular 3D object detection aims to predict the object location, dimension and orientation in 3D space alongside the object category given only a monocular image. It poses a great challenge due to its ill-posed property which is…

Semantic Scene Completion (SSC) is a critical task in computer vision, that utilized in applications such as virtual reality (VR). SSC aims to construct detailed 3D models from partial views by transforming a single 2D image into a 3D…

Recent years have seen a surge of interest in anomaly detection for tackling industrial defect detection, event detection, etc. However, existing unsupervised anomaly detectors, particularly those for the vision modality, face significant…

Domain generalized semantic segmentation is an essential computer vision task, for which models only leverage source data to learn the capability of generalized semantic segmentation towards the unseen target domains. Previous works…

To achieve accurate and robust object detection in the real-world scenario, various forms of images are incorporated, such as color, thermal, and depth. However, multimodal data often suffer from the position shift problem, i.e., the image…

Within (semi-)automated visual industrial inspection, learning-based approaches for assessing visual defects, including deep neural networks, enable the processing of otherwise small defect patterns in pixel size on high-resolution imagery.…

Zero-Shot Anomaly Detection (ZSAD) leverages Vision-Language Models (VLMs) to enable supervision-free industrial inspection. However, existing ZSAD paradigms are constrained by single visual backbones, which struggle to balance global…

Zero-shot 3D anomaly detection aims to identify anomalies without access to training data from target categories. However, existing methods mainly rely on projecting 3D observations into multi-view representations that primarily capture…

Traditional synthetic aperture radar image change detection methods based on convolutional neural networks (CNNs) face the challenges of speckle noise and deformation sensitivity. To mitigate these issues, we proposed a Multiscale Capsule…

The core problem in multi-view anomaly detection is to represent local neighborhoods of normal instances consistently across all views. Recent approaches consider a representation of local neighborhood in each view independently, and then…

Multispectral pedestrian detection is a crucial component in various critical applications. However, a significant challenge arises due to the misalignment between these modalities, particularly under real-world conditions where data often…

Unaligned Scene Change Detection aims to detect scene changes between image pairs captured at different times without assuming viewpoint alignment. To handle viewpoint variations, current methods rely solely on 2D visual cues to establish…

3D face alignment of monocular images is a crucial process in the recognition of faces with disguise.3D face reconstruction facilitated by alignment can restore the face structure which is helpful in detcting disguise interference.This…

Simultaneous Localization and Mapping (SLAM) is one of the most essential techniques in many real-world robotic applications. The assumption of static environments is common in most SLAM algorithms, which however, is not the case for most…

Semantic anomalies are contextually invalid or unusual combinations of familiar visual elements that can cause undefined behavior and failures in system-level reasoning for autonomous systems. This work explores semantic anomaly detection…

Geometric knowledge has been shown to be beneficial for the stereo matching task. However, prior attempts to integrate geometric insights into stereo matching algorithms have largely focused on geometric knowledge from single images while…

Few-shot segmentation aims to segment unseen-class objects given only a handful of densely labeled samples. Prototype learning, where the support feature yields a singleor several prototypes by averaging global and local object information,…

Semantic matching aims to establish pixel-level correspondences between instances of the same category and represents a fundamental task in computer vision. Existing approaches suffer from two limitations: (i) Geometric Ambiguity: Their…