Related papers: What Can be Seen is What You Get: Structure Aware …
3D object detection task from lidar or camera sensors is essential for autonomous driving. Pioneer attempts at multi-modality fusion complement the sparse lidar point clouds with rich semantic texture information from images at the cost of…
Fine-tuning large pre-trained models with task-specific data has achieved great success in NLP. However, it has been demonstrated that the majority of information within the self-attention networks is redundant and not utilized effectively…
In this paper, we present a deep learning architecture which addresses the problem of 3D semantic segmentation of unstructured point clouds. Compared to previous work, we introduce grouping techniques which define point neighborhoods in the…
Understanding 3D point cloud models for learning purposes has become an imperative challenge for real-world identification such as autonomous driving systems. A wide variety of solutions using deep learning have been proposed for point…
Mobile robots and autonomous vehicles rely on multi-modal sensor setups to perceive and understand their surroundings. Aside from cameras, LiDAR sensors represent a central component of state-of-the-art perception systems. In addition to…
Labelling point clouds fully is highly time-consuming and costly. As larger point cloud datasets with billions of points become more common, we ask whether the full annotation is even necessary, demonstrating that existing baselines…
This study analyzes semantic segmentation performance across heterogeneously labeled point-cloud datasets relevant to public safety applications, including pre-incident planning systems derived from lidar scans. Using NIST's Point Cloud…
Point cloud segmentation is a fundamental task in 3D vision that serves a wide range of applications. Although great progresses have been made these years, its practical usability is still limited by the availability of training data.…
Novel class discovery (NCD) for semantic segmentation is the task of learning a model that can segment unlabelled (novel) classes using only the supervision from labelled (base) classes. This problem has recently been pioneered for 2D image…
The development of practical applications, such as autonomous driving and robotics, has brought increasing attention to 3D point cloud understanding. While deep learning has achieved remarkable success on image-based tasks, there are many…
We propose a novel approach to self-supervised learning of point cloud representations by differentiable neural rendering. Motivated by the fact that informative point cloud features should be able to encode rich geometry and appearance…
Data augmentation is a ubiquitous technique for increasing the size of labeled training sets by leveraging task-specific data transformations that preserve class labels. While it is often easy for domain experts to specify individual…
3D point clouds are discrete samples of continuous surfaces which can be used for various applications. However, the lack of true connectivity information, i.e., edge information, makes point cloud recognition challenging. Recent edge-aware…
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…
This paper presents a new 3D point cloud classification benchmark data set with over four billion manually labelled points, meant as input for data-hungry (deep) learning methods. We also discuss first submissions to the benchmark that use…
For the semantic segmentation of images, state-of-the-art deep neural networks (DNNs) achieve high segmentation accuracy if that task is restricted to a closed set of classes. However, as of now DNNs have limited ability to operate in an…
A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in 2D, whereas the domain gap between 2D and 3D creates a fundamental challenge. This paper proposes a novel approach to point-cloud…
Point cloud analysis is attracting attention from Artificial Intelligence research since it can be widely used in applications such as robotics, Augmented Reality, self-driving. However, it is always challenging due to irregularities,…
In this case study, we present a data-efficient point cloud segmentation pipeline and training framework for robust segmentation of unimproved roads and seven other classes. Our method employs a two-stage training framework: first, a…
Data augmentation is widely known as a simple yet surprisingly effective technique for regularizing deep networks. Conventional data augmentation schemes, e.g., flipping, translation or rotation, are low-level, data-independent and…