Related papers: One Metric to Measure them All: Localisation Recal…

Recognizing 3D objects in the presence of noise, varying mesh resolution, occlusion and clutter is a very challenging task. This paper presents a novel method named Rotational Projection Statistics (RoPS). It has three major modules: Local…

Autonomous driving relies on accurate perception to ensure safe driving. Collaborative perception improves accuracy by mitigating the sensing limitations of individual vehicles, such as limited perception range and occlusion-induced blind…

Camera pose estimation is a fundamental problem in robotics. This paper focuses on two issues of interest: First, point and line features have complementary advantages, and it is of great value to design a uniform algorithm that can fuse…

A significant portion of the literature on fault localization assumes (more or less explicitly) that there are sufficient reliable measurements to guarantee that the system is observable. While several heuristics exist to break the…

Developing an effective evaluation metric is crucial for accurately and swiftly measuring LiDAR perception performance. One major issue is the lack of metrics that can simultaneously generate fast and accurate evaluations based on either…

A fundamental limitation of object detectors is that they suffer from "spatial bias", and in particular perform less satisfactorily when detecting objects near image borders. For a long time, there has been a lack of effective ways to…

We propose a robust calibration pipeline that optimises the selection of calibration samples for the estimation of calibration parameters that fit the entire scene. We minimise user error by automating the data selection process according…

We present a single-shot, bottom-up approach for whole image parsing. Whole image parsing, also known as Panoptic Segmentation, generalizes the tasks of semantic segmentation for 'stuff' classes and instance segmentation for 'thing'…

Recognizing a previously visited place, also known as place recognition (or loop closure detection) is the key towards fully autonomous mobile robots and self-driving vehicle navigation. Augmented with various Simultaneous Localization and…

Driver monitoring systems require not just high accuracy but reliable, well-calibrated confidence scores for safety-critical deployment. While direct low-resolution training yields high overall accuracy, it produces poorly calibrated…

Radial velocity (RV) is crucial for stellar kinematics and Galactic archaeology. The Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST) has obtained over ten million low-resolution spectra ($R \sim 1800$), yielding RVs for…

In this work, we introduce the new scene understanding task of Part-aware Panoptic Segmentation (PPS), which aims to understand a scene at multiple levels of abstraction, and unifies the tasks of scene parsing and part parsing. For this…

Repetitive action counting (RAC) aims to estimate the number of class-agnostic action occurrences in a video without exemplars. Most current RAC methods rely on a raw frame-to-frame similarity representation for period prediction. However,…

In this work, we first tackle the problem of simultaneous pixel-level localization and image-level classification with only image-level labels for fully convolutional network training. We investigate the global pooling method which plays a…

This paper presents a novel calibration algorithm for Multi-Focus Plenoptic Cameras (MFPCs) using raw images only. The design of such cameras is usually complex and relies on precise placement of optic elements. Several calibration…

In the majority of object detection frameworks, the confidence of instance classification is used as the quality criterion of predicted bounding boxes, like the confidence-based ranking in non-maximum suppression (NMS). However, the quality…

Vision-Language Models (VLMs) demonstrate impressive capabilities across multimodal tasks, yet exhibit systematic spatial reasoning failures, achieving only 49% (CLIP) to 54% (BLIP-2) accuracy on basic directional relationships. For safe…

Part-aware panoptic segmentation (PPS) requires (a) that each foreground object and background region in an image is segmented and classified, and (b) that all parts within foreground objects are segmented, classified and linked to their…

Deploying object detection on microcontrollers (MCUs) enables intelligent edge devices but current models cannot learn new object categories after deployment. Existing continual learning methods require storing raw images far exceeding MCU…

Accurate labeling is essential for supervised deep learning methods. However, it is almost impossible to accurately and manually annotate thousands of images, which results in many labeling errors for most datasets. We proposes a local…