Related papers: 3DOS: Towards 3D Open Set Learning -- Benchmarking…

Industrial defect detection is vital for upholding product quality across contemporary manufacturing systems. As the expectations for precision, automation, and scalability intensify, conventional inspection approaches are increasingly…

Point clouds provide a flexible and natural representation usable in countless applications such as robotics or self-driving cars. Recently, deep neural networks operating on raw point cloud data have shown promising results on supervised…

Addressing Lidar Panoptic Segmentation (LPS ) is crucial for safe deployment of autonomous vehicles. LPS aims to recognize and segment lidar points w.r.t. a pre-defined vocabulary of semantic classes, including thing classes of countable…

We present a novel active learning framework for 3D point cloud semantic segmentation that, for the first time, integrates large language models (LLMs) to construct hierarchical label structures and guide uncertainty-based sample selection.…

Image classification methods are usually trained to perform predictions taking into account a predefined group of known classes. Real-world problems, however, may not allow for a full knowledge of the input and label spaces, making failures…

3D object detection plays a pivotal role in many applications, most notably autonomous driving and robotics. These applications are commonly deployed on edge devices to promptly interact with the environment, and often require near…

In recent years, modern techniques in deep learning and large-scale datasets have led to impressive progress in 3D instance segmentation, grasp pose estimation, and robotics. This allows for accurate detection directly in 3D scenes, object-…

In recent years, much progress has been made in LiDAR-based 3D object detection mainly due to advances in detector architecture designs and availability of large-scale LiDAR datasets. Existing 3D object detectors tend to perform well on the…

Existing point cloud semantic segmentation networks cannot identify unknown classes and update their knowledge, due to a closed-set and static perspective of the real world, which would induce the intelligent agent to make bad decisions. To…

We aim for domestic robots to perform long-term indoor service. Under the object-level scene dynamics induced by daily human activities, a robot needs to robustly localize itself in the environment subject to scene uncertainties. Previous…

Semantic 3D building models are widely available and used in numerous applications. Such 3D building models display rich semantics but no fa\c{c}ade openings, chiefly owing to their aerial acquisition techniques. Hence, refining models'…

The rapid progress in 3D scene understanding has come with growing demand for data; however, collecting and annotating 3D scenes (e.g. point clouds) are notoriously hard. For example, the number of scenes (e.g. indoor rooms) that can be…

The performance of domain adaptation technologies has not yet reached an ideal level in the current 3D object detection field for autonomous driving, which is mainly due to significant differences in the size of vehicles, as well as the…

In this work we present a novel approach to joint semantic localisation and scene understanding. Our work is motivated by the need for localisation algorithms which not only predict 6-DoF camera pose but also simultaneously recognise…

3D scene understanding is crucial for facilitating seamless interaction between digital devices and the physical world. Real-time capturing and processing of the 3D scene are essential for achieving this seamless integration. While existing…

Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous and…

Although self-supervised 3D anomaly detection assumes that acquiring high-precision point clouds is computationally expensive, in real manufacturing scenarios it is often feasible to collect a limited number of anomalous samples. Therefore,…

Most deep learning approaches to comprehensive semantic modeling of 3D indoor spaces require costly dense annotations in the 3D domain. In this work, we explore a central 3D scene modeling task, namely, semantic scene reconstruction without…

Adapting robot programmes to changes in the environment is a well-known industry problem, and it is the reason why many tedious tasks are not automated in small and medium-sized enterprises (SMEs). A semantic world model of a robot's…

We introduce a new setting of Novel Class Discovery in Semantic Segmentation (NCDSS), which aims at segmenting unlabeled images containing new classes given prior knowledge from a labeled set of disjoint classes. In contrast to existing…