Related papers: LIDARLearn: A Unified Deep Learning Library for 3D…

This paper describes an optimized single-stage deep convolutional neural network to detect objects in urban environments, using nothing more than point cloud data. This feature enables our method to work regardless the time of the day and…

Nowadays, pre-training big models on large-scale datasets has become a crucial topic in deep learning. The pre-trained models with high representation ability and transferability achieve a great success and dominate many downstream tasks in…

3D Point cloud registration is still a very challenging topic due to the difficulty in finding the rigid transformation between two point clouds with partial correspondences, and it's even harder in the absence of any initial estimation…

The manual annotation for large-scale point clouds costs a lot of time and is usually unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training and fine-tuning paradigm in both vision and language tasks,…

Recent advances in deep learning have significantly improved 3D semantic segmentation, but most models focus on indoor or terrestrial datasets. Their behavior under real aerial acquisition conditions remains insufficiently explored, and…

Unified segmentation of 3D point clouds is crucial for scene understanding, but is hindered by its sparse structure, limited annotations, and the challenge of distinguishing fine-grained object classes in complex environments. Existing…

Autonomous vehicles need to have a semantic understanding of the three-dimensional world around them in order to reason about their environment. State of the art methods use deep neural networks to predict semantic classes for each point in…

Impressive performance on point cloud semantic segmentation has been achieved by fully-supervised methods with large amounts of labelled data. As it is labour-intensive to acquire large-scale point cloud data with point-wise labels, many…

We introduce Point-LN, a novel lightweight framework engineered for efficient 3D point cloud classification. Point-LN integrates essential non-parametric components-such as Farthest Point Sampling (FPS), k-Nearest Neighbors (k-NN), and…

The remarkable breakthroughs in point cloud representation learning have boosted their usage in real-world applications such as self-driving cars and virtual reality. However, these applications usually have an urgent requirement for not…

We introduce ECLAIR (Extended Classification of Lidar for AI Recognition), a new outdoor large-scale aerial LiDAR dataset designed specifically for advancing research in point cloud semantic segmentation. As the most extensive and diverse…

Autonomous driving has achieved rapid development over the last few decades, including the machine perception as an important issue of it. Although object detection based on conventional cameras has achieved remarkable results in 2D/3D,…

Many existing approaches for 3D point cloud semantic segmentation are fully supervised. These fully supervised approaches heavily rely on large amounts of labeled training data that are difficult to obtain and cannot segment new classes…

While early AutoML frameworks focused on optimizing traditional ML pipelines and their hyperparameters, a recent trend in AutoML is to focus on neural architecture search. In this paper, we introduce Auto-PyTorch, which brings the best of…

3D Transformers have achieved great success in point cloud understanding and representation. However, there is still considerable scope for further development in effective and efficient Transformers for large-scale LiDAR point cloud scene…

LiDAR's dense, sharp point cloud (PC) representations of the surrounding environment enable accurate perception and significantly improve road safety by offering greater scene awareness and understanding. However, LiDAR's high cost…

Advanced sensors are a key to enable self-driving cars technology. Laser scanner sensors (LiDAR, Light Detection And Ranging) became a fundamental choice due to its long-range and robustness to low light driving conditions. The problem of…

3D point cloud semantic segmentation is one of the fundamental tasks for environmental understanding. Although significant progress has been made in recent years, the performance of classes with few examples or few points is still far from…

LiDAR sensors are often considered essential for autonomous driving, but high-resolution sensors remain expensive while affordable low-resolution sensors produce sparse point clouds that miss critical details. LiDAR super-resolution…

Point cloud registration involves aligning one point cloud with another or with a three-dimensional (3D) model, enabling the integration of multimodal data into a unified representation. This is essential in applications such as…