YAN Xu

Huawei Noah's Ark Lab

Chinese University of Hongkong, Shenzhen (CUHK-SZ)

Biography

I am currently a senior staff engineer at autonomous driving (AD) group of Huawei Noah's Ark Lab. I obtained my Ph.D. degree from the Programme of Computer & Information Engineering at The Chinese University of Hongkong, Shenzhen, supervised by Profs. Zhen Li and Shuguang Cui.

Always looking for research interns with strong CV/AD background, feel free to shoot an email if interested.

Current Interests

Foundation Model for AD
Large VLM for AD
Self-learning/Pre-training

Visiting Scholar

VAS group of Max Planck Institute for Informatics

Education

Ph.D. in Computer and Information Engineering, Oct 2023

Chinese University of Hongkong, Shenzhen
Master in Data Science, Dec 2020

Chinese University of Hongkong, Shenzhen
B.S in School of Mathematics, July 2018

Sun Yat-sen University

Challenge & Benchmark

[WorldModel@CVPR2024] Our method achieved 2nd place and innovative award in predictive world model chanllenge at CVPR2024! See our paper here.
[Occ&Flow@China3DV2024] Our method achieved 2nd place and innovative award in 3D occupancy and flow chanllenge at China3DV2024!
[Occ@CVPR2023] Our method RadOcc achieved 1st place in 3D occupancy prediction benchmark at CVPR2023!
[HOI4D@CVPR2023] I achieved 1st place and 3rd place in 4D semantic segmentation and 4D action segmentation tracks of HOI4D@CVPR2023!
[KITTI] Our method BEV@DC achieved 1st in the public leaderboard of KITTI depth completion benchmark (2022.11.11)!
[Urban3D@ECCV2022] I achieved 3rd place in semantic segmentation track of Urban3D@ECCV2022!
[SemanticKITTI] Our method 2DPASS achieved 1st in the public leaderboard of SemanticKITTI in both single and multiple scan(s) semantic segmentation tasks (2022.07.03)!
[Urban3D@ECCV2021] I achieved 2nd place in Urban3D@ICCV2021, and our codes are released here!
[SemanticKITTI] Our method JS3C-Net achieved 3rd and 1st in the public leaderboard of SemanticKITTI in semantic segmentation and scene completion tasks (2020.12.02)!

Publications

Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities

Survey

The first survey about forging vision foundation model for autonomous driving!

Xu Yan, Haiming Zhang, Yingjie Cai, Jingming Guo, Weichao Qiu, Bin Gao, Kaiqiang Zhou, Yue Zhao, Huan Jin, Jiantao Gao, Zhen Li, Lihui Jiang, Wei Zhang, Hongbo Zhang, Dengxin Dai, Bingbing Liu

Paper Project

RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation

AAAI2024 (* indicates corresponding author)

4th place in the challenge Occ3D@CVPR2023!

Haiming Zhang, Xu Yan*, Dongfeng Bai, Jiantao Gao, Pan Wang, Bingbing Liu, Shuguang Cui, Zhen Li

Paper

X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge Transfer

AAAI2024 (* indicates corresponding author)

1st and 3rd places in the challenge HOI4D@CVPR2023!

Linglin Jing, Ying Xue, Xu Yan*, Chaoda Zheng, Dong Wang, Ruimao Zhang, Zhigang Wang, Hui Fang, Bin Zhao, Zhen Li

Paper Code

An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds

TPAMI (* indicates co-first author)

Impact Factor: 23.6!

Chaoda Zheng, Xu Yan*, Haiming Zhang, Boyuan Wang, Shenghui Cheng, Zhen Li, Shuguang Cui

Paper Project Code

LATR: 3D Lane Detection from Monocular Images with Transformer

ICCV2023

Oral Presentation! (5% in submission)

Yueru Luo, Chaoda Zheng, Xu Yan, Kun Tang, Chao Zheng, Shuguang Cui, Zhen Li

Paper Code

CPU: Codebook Lookup Transformer with Knowledge Distillation for Point Cloud Upsampling

International Multimedia Conference (MM) 2023

Weibing Zhao, Haiming Zhang, Chaoda Zheng, Xu Yan Shuguang Cui, Zhen Li

Paper

Efficient and Robust Video Object Segmentation through Isogenous Memory Sampling and Frame Relation Mining

IEEE Transactions on Image Processing (TIP)

Impact Factor: 10.6

Jisheng Dang, Huicheng Zheng, Jinming Lai, Xu Yan, Yulan Guo

Paper

BEV@DC: Birds-Eye View Assisted Training for Depth Completion

CVPR2023

Rank 1st in the leaderboard of KITTI depth completion (2022-11-16)!

Wending Zhou, Xu Yan, Yinghong Liao, Yuankai Lin, Jin Huang, Gangming Zhao, Shuguang Cui, Zhen Li

Paper

Benchmarking the Robustness of LiDAR Semantic Segmentation Models

International Journal of Computer Vision (IJCV)

Impact factor: 19.5!

Xu Yan, Chaoda Zheng, Zhen Li, Shuguang Cui, Dengxin Dai

Paper Project

Spatio-temporal Contextual Learning for Single Object Tracking on Point Clouds

TNNLS (* indicates co-first and correspondence author)

Impact Factor: 14.3!

Jiantao Gao, Xu Yan*, Weibing Zhao, Zhen Lyu, Yinghong Liao, Chaoda Zheng

Paper

Geometry-Aware Network for Domain Adaptive Semantic Segmentation

AAAI 2023

Yinghong Liao, Wending Zhou, Xu Yan, Yizhou Yu, Shuguang Cui, Zhen Li

Paper Code

MM-3DLaneNet: Multi-Modal 3D Lane Detection

arXiv

Yueru Luo, Xu Yan, Chaoda Zheng, Chao Zheng, Shuqi Mei, Tang Kun, Shuguang Cui, Zhen Li

Paper Code

Let Images Give You More: Point Cloud Cross-Modal Training for Shape Analysis

NeurIPS 2022

Spotlight! (5% in submission)

Xu Yan, Heshen Zhan, Chaoda Zheng, Jiantao Gao, Ruimao Zhang, Shuguang Cui, Zhen Li

Paper Code

2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds

ECCV 2022

Rank 1st in the leaderboard of SemanticKITTI (2022-03-08)!

Xu Yan, Jiantao Gao, Chaoda Zheng, Chao Zheng, Ruimao Zhang, Shuguang Cui, Zhen Li

Paper Code

Toward Explainable and Fine-Grained 3D Grounding through Referring Textual Phrases

TNNLS (* indicates co-first author)

Impact Factor: 14.3! Newly proposed benchmark for 3D visual grounding!

Zhihao Yuan, Xu Yan*, Zhuo Li, Xuhao Li, Yao Guo, Shuguang Cui, Zhen Li

Paper Project Code

Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulation

IEEE Transactions on Visualization and Computer Graphics (TVCG)

Newly proposed dataset for VQA-3D!

Xu Yan, Zhihao Yuan, Yuhao Du, Yinghong Liao, Yao Guo, Zhen Li,
Shuguang Cui

Paper Code

Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds

CVPR 2022

Oral Presentation! (5% in submission)

Chaoda Zheng, Xu Yan, Haiming Zhang, Boyuan Wang, Shenghui Cheng, Zhen Li, Shuguang Cui

Paper Project Code

X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning

CVPR 2022 (* indicates co-first author)

Zhihao Yuan, Xu Yan*, Yinghong Liao, Yao Guo, Guanbin Li, Zhen Li,
Shuguang Cui

Paper Code

Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds

ICCV 2021 (* indicates co-first author)

Chaoda Zheng, Xu Yan*, Jiantao Gao, Weibing Zhao, Wei Zhang, Zhen Li, Shuguang Cui

Paper Code

InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring

ICCV 2021 (* indicates co-first author)

Rank 1st in the leaderboard of ScanRefer (2021-03-18)!

Zhihao Yuan, Xu Yan*, Yinghong Liao, Ruimao Zhang, Zhen Li, Shuguang Cui

Paper Code

PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery

IJCAI 2021 (* indicates co-first author)

Only 13.9% acceptance rate！

Weibing Zhao, Xu Yan*, Jiantao Gao, Ruimao Zhang, Jiayan Zhang, Zhen Li, Song Wu, Shuguang Cui

Paper Code

Geometric Morphology based Irrelevant Vessels Removal for Accurate Coronary Artery Segmentation

ISBI 2021 (* indicates co-first author)

Qin Wang, Weibing Zhao*, Xu Yan*, Hui Che, Kunlin Ye, Yingfeng Lu, Zhen Li, Shuguang Cui

Paper Dataset (CORONARY-48)

Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion

AAAI 2021

Rank 1st and 3rd in the semantic scene completion and semantic segmentation leaderboards of SemanticKITTI (2020-09-18)！

Xu Yan, Jiantao Gao, Jie Li, Ruimao Zhang, Zhen Li, Rui Huang, Shuguang Cui

Paper Poster Code

Towards Content-Independent Multi-Reference Super-Resolution: Adaptive Pattern Matching and Feature Aggregation

ECCV 2020

Xu Yan, Weibing Zhao, Kun Yuan, Sheng Wang, Zhen Li, Shuguang Cui

Paper

PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling

CVPR 2020

Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui

Paper Poster Video Code

PointSite: A Point Cloud Segmentation Tool for Identification of Protein Ligand Binding Atoms

Journal of Chemical Information and Modeling

(Impact factor: 4.956)

Xu Yan, Yingfeng Lu, Zhen Li, Qing Wei, Xin Gao, Sheng Wang, Song Wu, Shuguang Cui

Paper Code

An Efficient Hybrid Model for Kidney Tumor Segmentation in CT Images

ISBI 2020

Xu Yan, Kun Yuan, Weibing Zhao, Sheng Wang, Zhen Li, Shuguang Cui

Paper

YAN Xu

Huawei Noah's Ark Lab

Chinese University of Hongkong, Shenzhen (CUHK-SZ)

Biography

Current Interests

Visiting Scholar

Education

Recent News

Challenge & Benchmark

Publications

Projects

Contact