Abstract 3D synthetic-to-real unsupervised domain adaptive segmentation is crucial to
annotating new domains. Self-training is a competitive approach for this task but its …

Abstract 3D point cloud segmentation has received significant interest for its growing
applications. However, the generalization ability of models suffers in dynamic scenarios due …

Autonomous driving technology has achieved remarkable advancements, offering
substantial potential to revolutionize traffic safety and smart mobility. However, when faced …

Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable
challenge, primarily stemming from the sparse and unordered nature of point cloud data …

In this paper, we present PCoTTA, an innovative, pioneering framework for Continual Test-
Time Adaptation (CoTTA) in multi-task point cloud understanding, enhancing the model's …

Abstract Addressing Lidar Panoptic Segmentation (LPS) is crucial for safe deployment of
autnomous vehicles. LPS aims to recognize and segment lidar points wrt a pre-defined …

In the realm of LiDAR-based perception, significant strides have been made, yet domain
generalization remains a substantial challenge. The performance often deteriorates when …

In this paper, we propose LiOn-XA, an unsupervised domain adaptation (UDA) approach
that combines LiDAR-Only Cross-Modal (X) learning with Adversarial training for 3D LiDAR …

3D LiDAR-based perception has made remarkable advancements, leading to the
widespread adoption of LiDAR in autonomous driving systems. Despite these technological …

While significant progress has been achieved in LiDAR-based perception, domain
generalization continues to present challenges, often resulting in reduced performance …