Related papers: THOR2: Topological Analysis for 3D Shape and Color…
Both humans and deep learning models can recognize objects from 3D shapes depicted with sparse visual information, such as a set of points randomly sampled from the surfaces of 3D objects (termed a point cloud). Although deep learning…
Embodied perception is essential for intelligent vehicles and robots in interactive environmental understanding. However, these advancements primarily focus on vision, with limited attention given to using 3D modeling sensors, restricting a…
Two-dimensional (2D) carbon networks, from pristine graphene to defect-rich and amorphous monolayers, exhibit a complex structure-energy landscape governed not only by local bonding but also by medium-range order and network topology.…
Objective - This study presents a biometric identification method based on topological invariants from 2D iris images, representing iris texture via formally defined digital homology and evaluating classification performance. Methods - Each…
Cooperative perception offers several benefits for enhancing the capabilities of autonomous vehicles and improving road safety. Using roadside sensors in addition to onboard sensors increases reliability and extends the sensor range.…
Despite the recent success of state-of-the-art 3D object recognition approaches, service robots are frequently failed to recognize many objects in real human-centric environments. For these robots, object recognition is a challenging task…
Learning semantic representations from point sets of 3D object shapes is often challenged by significant geometric variations, primarily due to differences in data acquisition methods. Typically, training data is generated using point…
Place Recognition enables the estimation of a globally consistent map and trajectory by providing non-local constraints in Simultaneous Localisation and Mapping (SLAM). This paper presents Locus, a novel place recognition method using 3D…
Advances in LiDAR sensors provide rich 3D data that supports 3D scene understanding. However, due to occlusion and signal miss, LiDAR point clouds are in practice 2.5D as they cover only partial underlying shapes, which poses a fundamental…
LiDAR-based place recognition serves as a crucial enabler for long-term autonomy in robotics and autonomous driving systems. Yet, prevailing methodologies relying on handcrafted feature extraction face dual challenges: (1) Inconsistent…
Good pre-trained visual representations could enable robots to learn visuomotor policy efficiently. Still, existing representations take a one-size-fits-all-tasks approach that comes with two important drawbacks: (1) Being completely…
Camouflaged object detection (COD) aims to identify the objects that conceal themselves in natural scenes. Accurate COD suffers from a number of challenges associated with low boundary contrast and the large variation of object appearances,…
Change detection and irregular object extraction in 3D point clouds is a challenging task that is of high importance not only for autonomous navigation but also for updating existing digital twin models of various industrial environments.…
Tiny object detection is one of the key challenges in the field of object detection. The performance of most generic detectors dramatically decreases in tiny object detection tasks. The main challenge lies in extracting effective features…
One of the essential tasks in connectomics is the morphology analysis of neurons and organelles like mitochondria to shed light on their biological properties. However, these biological objects often have tangled parts or complex branching…
Recent advances in pretraining 3D point cloud encoders (e.g., Point-BERT, Point-MAE) have produced powerful models, whose abilities are typically evaluated on geometric or semantic tasks. At the same time, topological descriptors have been…
We present THUNDR, a transformer-based deep neural network methodology to reconstruct the 3d pose and shape of people, given monocular RGB images. Key to our methodology is an intermediate 3d marker representation, where we aim to combine…
In artificial-intelligence-aided signal processing, existing deep learning models often exhibit a black-box structure, and their validity and comprehensibility remain elusive. The integration of topological methods, despite its relatively…
Methods from computational topology are becoming more and more popular in computer vision and have shown to improve the state-of-the-art in several tasks. In this paper, we investigate the applicability of topological descriptors in the…
Object shape is a key cue that contributes to the semantic understanding of objects. In this work we focus on the categorization of real-world object point clouds to particular shape types. Therein surface description and representation of…