Author name cluster

Boyi Sun

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

2 author rows

AAAI Conference 2025 Conference Paper

3D Annotation-Free Learning by Distilling 2D Open-Vocabulary Segmentation Models for Autonomous Driving

Boyi Sun
Yuhang Liu
Xingxia Wang
Bin Tian
Long Chen
Fei-Yue Wang

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 propose AFOV, a novel 3D Annotation-Free framework assisted by 2D Open-Vocabulary segmentation models. It consists of two stages: In the first stage, we innovatively integrate high-quality textual and image features of 2D open-vocabulary models and propose the Tri-Modal contrastive Pre-training (TMP). In the second stage, spatial mapping between point clouds and images is utilized to generate pseudo-labels, enabling cross-modal knowledge distillation. Besides, we introduce the Approximate Flat Interaction (AFI) to address the noise during alignment and label confusion. To validate the superiority of AFOV, extensive experiments are conducted on multiple related datasets. We achieved a record-breaking 47.73% mIoU on the annotation-free 3D segmentation task in nuScenes, surpassing the previous best model by 3.13% mIoU. Meanwhile, the performance of fine-tuning with 1% data on nuScenes and SemanticKITTI reached a remarkable 51.75% mIoU and 48.14% mIoU, outperforming all previous pre-trained models.

PDF Details DOI

IROS Conference 2025 Conference Paper

HPLaw: Heterogeneous Parallel LiDARs for Adverse Weather in V2V

Yuhang Liu
Xinyue Ma
Xingxia Wang
Boyi Sun
Yutong Wang 0001
Fenghua Zhu
Fei-Yue Wang 0001

Parallel LiDAR emerges as an innovative framework for next-generation intelligent LiDAR systems in autonomous driving. In parallel LiDAR research, V2V (Vehicle-to-Vehicle) cooperative perception is a promising technology which can effectively enhance perception range and accuracy through inter-agent information exchange. Currently, sensor heterogeneity remains a critical challenge in V2V. Although some work has made initial attempts to address this issue, existing studies are primarily conducted under ideal clear-weather conditions, ignoring the impact of variable weather factors in real-world applications. In fact, adverse weather has been shown to significantly degrade the performance of LiDAR systems, with the risk of cumulative degradation in V2V. To address this challenge, we first introduce OPV2V-W and V2V4Real-W as new benchmarks to study sensor heterogeneity in V2V under adverse weather. Then we propose the HPLaw architecture (Heterogeneous Parallel LiDARs for Adverse Weather), a self-knowledge distillation method designed to enhance model robustness across varying weather scenarios. HPLaw employs an efficient PF network to facilitate heterogeneous feature fusion and incorporates an SAKD module to extract weather-invariant features. Extensive experiments demonstrate that the student model in HPLaw achieves outstanding performance under all weather conditions, exhibiting remarkable robustness.

Details

ICRA Conference 2024 Conference Paper

HPL-ViT: A Unified Perception Framework for Heterogeneous Parallel LiDARs in V2V

Yuhang Liu
Boyi Sun
Yuke Li
Yuzheng Hu
Fei-Yue Wang 0001

To develop the next generation of intelligent LiDARs, we propose a novel framework of parallel LiDARs and construct a hardware prototype in our experimental platform, DAWN (Digital Artificial World for Natural). It emphasizes the tight integration of physical and digital space in LiDAR systems, with networking being one of its supported core features. In the context of autonomous driving, V2V (Vehicle-to-Vehicle) technology enables efficient information sharing between different agents which significantly promotes the development of LiDAR networks. However, current research operates under an ideal situation where all vehicles are equipped with identical LiDAR, ignoring the diversity of LiDAR categories and operating frequencies. In this paper, we first utilize OpenCDA and RLS (Realistic LiDAR Simulation) to construct a novel heterogeneous LiDAR dataset named OPV2V-HPL. Additionally, we present HPL-ViT, a pioneering architecture designed for robust feature fusion in heterogeneous and dynamic scenarios. It uses a graph-attention Transformer to extract domain-specific features for each agent, coupled with a cross-attention mechanism for the final fusion. Extensive experiments on OPV2V-HPL demonstrate that HPL-ViT achieves SOTA (state-of-the-art) performance in all settings and exhibits outstanding generalization capabilities.

Details