Related papers: SALT: A Flexible Semi-Automatic Labeling Tool for …

Large labeled data sets are one of the essential basics of modern deep learning techniques. Therefore, there is an increasing need for tools that allow to label large amounts of data as intuitively as possible. In this paper, we introduce…

We propose the SAL (Segment Anything in Lidar) method consisting of a text-promptable zero-shot model for segmenting and classifying any object in Lidar, and a pseudo-labeling engine that facilitates model training without manual…

We present a novel method, SALAD, for the challenging vision task of adapting a pre-trained "source" domain network to a "target" domain, with a small budget for annotation in the "target" domain and a shift in the label space. Further, the…

Zero-shot 4D segmentation and recognition of arbitrary objects in Lidar is crucial for embodied navigation, with applications ranging from streaming perception to semantic mapping and localization. However, the primary challenge in…

We propose SALT (Split-Adaptive Lightweight Tuning), a lightweight model adaptation framework for Split Computing under closed constraints, where the head and tail networks are proprietary and inaccessible to users. In such closed…

LiDAR odometry estimation and 3D semantic segmentation are crucial for autonomous driving, which has achieved remarkable advances recently. However, these tasks are challenging due to the imbalance of points in different semantic categories…

Split Computing enables collaborative inference between edge devices and the cloud by partitioning a deep neural network into an edge-side head and a server-side tail, reducing latency and limiting exposure of raw input data. However,…

LiDAR (Light Detection And Ranging) is an essential and widely adopted sensor for autonomous vehicles, particularly for those vehicles operating at higher levels (L4-L5) of autonomy. Recent work has demonstrated the promise of deep-learning…

Annotating 3D LiDAR point clouds for perception tasks is fundamental for many applications e.g., autonomous driving, yet it still remains notoriously labor-intensive. Pretraining-finetuning approach can alleviate the labeling burden by…

Whilst the availability of 3D LiDAR point cloud data has significantly grown in recent years, annotation remains expensive and time-consuming, leading to a demand for semi-supervised semantic segmentation methods with application domains…

Semantic segmentation of LiDAR point clouds is an important task in autonomous driving. However, training deep models via conventional supervised methods requires large datasets which are costly to label. It is critical to have…

In autonomous driving, the novel objects and lack of annotations challenge the traditional 3D LiDAR semantic segmentation based on deep learning. Few-shot learning is a feasible way to solve these issues. However, currently few-shot…

Learning 3D geometry directly from raw data, such as point clouds, triangle soups, or unoriented meshes is still a challenging task that feeds many downstream computer vision and graphics applications. In this paper, we introduce SALD: a…

The complex nature of medical image segmentation calls for models that are specifically designed to capture detailed, domain-specific features. Large foundation models offer considerable flexibility, yet the cost of fine-tuning these models…

Although data is abundant, data labeling is expensive. Semi-supervised learning methods combine a few labeled samples with a large corpus of unlabeled data to effectively train models. This paper introduces our proposed method LiDAM, a…

Unsupervised domain adaptation aims to transfer and adapt knowledge learned from a labeled source domain to an unlabeled target domain. Key components of unsupervised domain adaptation include: (a) maximizing performance on the target, and…

In the field of SLAM (Simultaneous Localization And Mapping) for robot navigation, mapping the environment is an important task. In this regard the Lidar sensor can produce near accurate 3D map of the environment in the format of point…

Weakly supervised LiDAR semantic segmentation has made significant strides with limited labeled data. However, most existing methods focus on the network training under weak supervision, while efficient annotation strategies remain largely…

Accurate 3D point cloud map generation is a core task for various robot missions or even for data-driven urban analysis. To do so, light detection and ranging (LiDAR) sensor-based simultaneous localization and mapping (SLAM) technology have…

Densely annotating LiDAR point clouds is costly, which restrains the scalability of fully-supervised learning methods. In this work, we study the underexplored semi-supervised learning (SSL) in LiDAR segmentation. Our core idea is to…