Related papers: VESPA: Towards un(Human)supervised Open-World Poin…

Annotated 3D scene data is scarce and expensive to acquire, while abundant unlabeled videos are readily available on the internet. In this paper, we demonstrate that carefully designed data engines can leverage web-curated, unlabeled videos…

This paper presents a novel approach to Single-Positive Multi-label Learning. In general multi-label learning, a model learns to predict multiple labels or categories for a single input image. This is in contrast with standard multi-class…

Autonomous driving requires the inference of actionable information such as detecting and classifying objects, and determining the drivable space. To this end, we present Multi-View LidarNet (MVLidarNet), a two-stage deep neural network for…

We propose a novel scene flow method that captures 3D motions from point clouds without relying on ground-truth scene flow annotations. Due to the irregularity and sparsity of point clouds, it is expensive and time-consuming to acquire…

In Autonomous Driving (AD), detection and tracking of obstacles on the roads is a critical task. Deep-learning based methods using annotated LiDAR data have been the most widely adopted approach for this. Unfortunately, annotating 3D point…

Image instance segmentation is a fundamental research topic in autonomous driving, which is crucial for scene understanding and road safety. Advanced learning-based approaches often rely on the costly 2D mask annotations for training. In…

Existing LiDAR-based 3D object detectors typically rely on manually annotated labels for training to achieve good performance. However, obtaining high-quality 3D labels is time-consuming and labor-intensive. To address this issue, recent…

For autonomous vehicles, driving safely is highly dependent on the capability to correctly perceive the environment in 3D space, hence the task of 3D object detection represents a fundamental aspect of perception. While 3D sensors deliver…

Voxel-based methods have achieved state-of-the-art performance for 3D object detection in autonomous driving. However, their significant computational and memory costs pose a challenge for their application to resource-constrained vehicles.…

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…

Monocular 3D object detection (M3OD) has long faced challenges due to data scarcity caused by high annotation costs and inherent 2D-to-3D ambiguity. Although various weakly supervised methods and pseudo-labeling methods have been proposed…

In perception for automated vehicles, safety is critical not only for the driver but also for other agents in the scene, particularly vulnerable road users such as pedestrians and cyclists. Previous representation methods, such as Bird's…

Autonomous vehicles rely on camera, LiDAR, and radar sensors to navigate the environment. Adverse weather conditions like snow, rain, and fog are known to be problematic for both camera and LiDAR-based perception systems. Currently, it is…

Vision-language models (VLMs), e.g., CLIP, have shown remarkable potential in zero-shot image classification. However, adapting these models to new domains remains challenging, especially in unsupervised settings where labeled data is…

Recognizing human actions from point cloud videos has attracted tremendous attention from both academia and industry due to its wide applications like automatic driving, robotics, and so on. However, current methods for point cloud action…

Great labels make great models. However, traditional labeling approaches for tasks like object detection have substantial costs at scale. Furthermore, alternatives to fully-supervised object detection either lose functionality or require…

We study an unsupervised domain adaptation problem for the semantic labeling of 3D point clouds, with a particular focus on domain discrepancies induced by different LiDAR sensors. Based on the observation that sparse 3D point clouds are…

Deep learning models for self-driving cars require a diverse training dataset to manage critical driving scenarios on public roads safely. This includes having data from divergent trajectories, such as the oncoming traffic lane or…

Research connecting text and images has recently seen several breakthroughs, with models like CLIP, DALL-E 2, and Stable Diffusion. However, the connection between text and other visual modalities, such as lidar data, has received less…

Point cloud data labeling is considered a time-consuming and expensive task in autonomous driving, whereas annotation-free learning training can avoid it by learning point cloud representations from unannotated data. In this paper, we…