Related papers: Lidar Panoptic Segmentation in an Open World

Panoptic segmentation is an important computer vision task which combines semantic and instance segmentation. It plays a crucial role in domains of medical image analysis, self-driving vehicles, and robotics by providing a comprehensive…

Understanding the surrounding environment is fundamental in autonomous driving and robotic perception. Distinguishing between known classes and previously unseen objects is crucial in real-world environments, as done in Anomaly…

Panoptic segmentation brings together two separate tasks: instance and semantic segmentation. Although they are related, unifying them faces an apparent paradox: how to learn simultaneously instance-specific and category-specific (i.e.…

Self-supervised learning (SSL) has the potential to benefit many applications, particularly those where manually annotating data is cumbersome. One such situation is the semantic segmentation of point clouds. In this context, existing…

Semantic segmentation for autonomous driving is an even more challenging task when faced with adverse driving conditions. Standard models trained on data recorded under ideal conditions show a deteriorated performance in unfavorable weather…

LiDAR point cloud semantic segmentation is essential for interpreting 3D environments in applications such as autonomous driving and robotics. Recent methods achieve strong performance by exploiting different point cloud representations or…

We propose DOPS, a fast single-stage 3D object detection method for LIDAR data. Previous methods often make domain-specific design decisions, for example projecting points into a bird-eye view image in autonomous driving scenarios. In…

Panoptic segmentation methods assign a known class to each pixel given in input. Even for state-of-the-art approaches, this inevitably enforces decisions that systematically lead to wrong predictions for objects outside the training…

Existing open-world universal segmentation approaches usually leverage CLIP and pre-computed proposal masks to treat open-world segmentation tasks as proposal classification. However, 1) these works cannot handle universal segmentation in…

Traditional semantic segmentation methods can recognize at test time only the classes that are present in the training set. This is a significant limitation, especially for semantic segmentation algorithms mounted on intelligent autonomous…

3D point cloud panoptic segmentation is the combined task to (i) assign each point to a semantic class and (ii) separate the points in each class into object instances. Recently there has been an increased interest in such comprehensive 3D…

This paper addresses the semantic instance segmentation task in the open-set conditions, where input images can contain known and unknown object classes. The training process of existing semantic instance segmentation methods requires…

In recent years, computer vision has transformed fields such as medical imaging, object recognition, and geospatial analytics. One of the fundamental tasks in computer vision is semantic image segmentation, which is vital for precise object…

Open-world instance-level scene understanding aims to locate and recognize unseen object categories that are not present in the annotated dataset. This task is challenging because the model needs to both localize novel 3D objects and infer…

Semantic segmentation in autonomous driving predominantly focuses on learning from large-scale data with a closed set of known classes without considering unknown objects. Motivated by safety reasons, we address the video class agnostic…

Existing 3D instance segmentation methods typically assume that all semantic classes to be segmented would be available during training and only seen categories are segmented at inference. We argue that such a closed-world assumption is…

Panoptic Segmentation aims to provide an understanding of background (stuff) and instances of objects (things) at a pixel level. It combines the separate tasks of semantic segmentation (pixel level classification) and instance segmentation…

There has been significant progress made in the field of autonomous vehicles. Object detection and tracking are the primary tasks for any autonomous vehicle. The task of object detection in autonomous vehicles relies on a variety of sensors…

As the exorbitant expense of labeling autopilot datasets and the growing trend of utilizing unlabeled data, semi-supervised segmentation on point clouds becomes increasingly imperative. Intuitively, finding out more ``unspoken words''…

During the last few years, continual learning (CL) strategies for image classification and segmentation have been widely investigated designing innovative solutions to tackle catastrophic forgetting, like knowledge distillation and…