1 code implementation • 8 May 2024 • Lingdong Kong, Xiang Xu, Jiawei Ren, Wenwei Zhang, Liang Pan, Kai Chen, Wei Tsang Ooi, Ziwei Liu
Efficient data utilization is crucial for advancing 3D scene understanding in autonomous driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully supervised methods.
1 code implementation • 8 May 2024 • Lingdong Kong, Youquan Liu, Lai Xing Ng, Benoit R. Cottereau, Wei Tsang Ooi
Event-based semantic segmentation (ESS) is a fundamental yet challenging task for event camera sensing.
no code implementations • 2 May 2024 • Youquan Liu, Lingdong Kong, Xiaoyang Wu, Runnan Chen, Xin Li, Liang Pan, Ziwei Liu, Yuexin Ma
A unified and versatile LiDAR segmentation model with strong robustness and generalizability is desirable for safe autonomous driving perception.
1 code implementation • 25 Mar 2024 • Lingdong Kong, Xiang Xu, Jun Cen, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu
Safety-critical 3D scene understanding tasks necessitate not only accurate but also confident predictions from 3D perception models.
1 code implementation • 25 Mar 2024 • Ye Li, Lingdong Kong, Hanjiang Hu, Xiaohao Xu, Xiaonan Huang
The robustness of driving perception systems under unprecedented conditions is crucial for safety-critical usages.
1 code implementation • 15 Mar 2024 • Jingyi Xu, Weidong Yang, Lingdong Kong, Youquan Liu, Rui Zhang, Qingyuan Zhou, Ben Fei
Then, another VFM trained on fine-grained 2D masks is adopted to guide the generation of semantically augmented images and point clouds to enhance the performance of neural networks, which mix the data from source and target domains like view frustums (FrustumMixing).
2 code implementations • 7 Dec 2023 • Xiang Xu, Lingdong Kong, Hui Shuai, Qingshan Liu
LiDAR segmentation has become a crucial component in advanced autonomous driving systems.
Ranked #2 on 3D Semantic Segmentation on nuScenes
1 code implementation • NeurIPS 2023 • Lingdong Kong, Shaoyuan Xie, Hanjiang Hu, Lai Xing Ng, Benoit R. Cottereau, Wei Tsang Ooi
Depth estimation from monocular images is pivotal for real-world visual perception systems.
no code implementations • 13 Oct 2023 • Xidong Peng, Runnan Chen, Feng Qiao, Lingdong Kong, Youquan Liu, Tai Wang, Xinge Zhu, Yuexin Ma
Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable challenge, primarily stemming from the sparse and unordered nature of point cloud data.
1 code implementation • ICCV 2023 • Youquan Liu, Runnan Chen, Xin Li, Lingdong Kong, Yuchen Yang, Zhaoyang Xia, Yeqi Bai, Xinge Zhu, Yuexin Ma, Yikang Li, Yu Qiao, Yuenan Hou
Besides, we construct the OpenPCSeg codebase, which is the largest and most comprehensive outdoor LiDAR segmentation codebase.
Ranked #2 on 3D Semantic Segmentation on SemanticKITTI (using extra training data)
1 code implementation • 27 Jul 2023 • Lingdong Kong, Yaru Niu, Shaoyuan Xie, Hanjiang Hu, Lai Xing Ng, Benoit R. Cottereau, Ding Zhao, Liangjun Zhang, Hesheng Wang, Wei Tsang Ooi, Ruijie Zhu, Ziyang Song, Li Liu, Tianzhu Zhang, Jun Yu, Mohan Jing, Pengwei Li, Xiaohua Qi, Cheng Jin, Yingfeng Chen, Jie Hou, Jie Zhang, Zhen Kan, Qiang Ling, Liang Peng, Minglei Li, Di Xu, Changpeng Yang, Yuanqi Yao, Gang Wu, Jian Kuai, Xianming Liu, Junjun Jiang, Jiamian Huang, Baojun Li, Jiale Chen, Shuang Zhang, Sun Ao, Zhenyu Li, Runze Chen, Haiyong Luo, Fang Zhao, Jingze Yu
In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation.
2 code implementations • NeurIPS 2023 • Youquan Liu, Lingdong Kong, Jun Cen, Runnan Chen, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu
Recent advancements in vision foundation models (VFMs) have opened up new possibilities for versatile and efficient visual perception.
1 code implementation • NeurIPS 2023 • Runnan Chen, Youquan Liu, Lingdong Kong, Nenglun Chen, Xinge Zhu, Yuexin Ma, Tongliang Liu, Wenping Wang
For nuImages and nuScenes datasets, the performance is 22. 1\% and 26. 8\% with improvements of 3. 5\% and 6. 0\%, respectively.
1 code implementation • 23 May 2023 • Jun Cen, Yizheng Wu, Kewei Wang, Xingyi Li, Jingkang Yang, Yixuan Pei, Lingdong Kong, Ziwei Liu, Qifeng Chen
The Segment Anything Model (SAM) has demonstrated its effectiveness in segmenting any part of 2D RGB images.
Open Vocabulary Semantic Segmentation Panoptic Segmentation +1
1 code implementation • 13 Apr 2023 • Shaoyuan Xie, Lingdong Kong, Wenwei Zhang, Jiawei Ren, Liang Pan, Kai Chen, Ziwei Liu
Our experiments further demonstrate that pre-training and depth-free BEV transformation has the potential to enhance out-of-distribution robustness.
1 code implementation • ICCV 2023 • Lingdong Kong, Youquan Liu, Xin Li, Runnan Chen, Wenwei Zhang, Jiawei Ren, Liang Pan, Kai Chen, Ziwei Liu
The robustness of 3D perception systems under natural corruptions from environments and sensors is pivotal for safety-critical applications.
no code implementations • ICCV 2023 • Lingdong Kong, Youquan Liu, Runnan Chen, Yuexin Ma, Xinge Zhu, Yikang Li, Yuenan Hou, Yu Qiao, Ziwei Liu
We show that, for the first time, a range view method is able to surpass the point, voxel, and multi-view fusion counterparts in the competing LiDAR semantic and panoptic segmentation benchmarks, i. e., SemanticKITTI, nuScenes, and ScribbleKITTI.
Ranked #4 on 3D Semantic Segmentation on SemanticKITTI
1 code implementation • CVPR 2023 • Runnan Chen, Youquan Liu, Lingdong Kong, Xinge Zhu, Yuexin Ma, Yikang Li, Yuenan Hou, Yu Qiao, Wenping Wang
For the first time, our pre-trained network achieves annotation-free 3D semantic segmentation with 20. 8% and 25. 08% mIoU on nuScenes and ScanNet, respectively.
1 code implementation • NeurIPS 2023 • Pengfei Wei, Lingdong Kong, Xinghua Qu, Yi Ren, Zhiqiang Xu, Jing Jiang, Xiang Yin
Specifically, we consider the generation of cross-domain videos from two sets of latent factors, one encoding the static information and another encoding the dynamic information.
2 code implementations • CVPR 2023 • Lingdong Kong, Jiawei Ren, Liang Pan, Ziwei Liu
Densely annotating LiDAR point clouds is costly, which restrains the scalability of fully-supervised learning methods.
1 code implementation • 30 Nov 2021 • Lingdong Kong, Niamul Quader, Venice Erin Liong
We present ConDA, a concatenation-based domain adaptation framework for LiDAR segmentation that: 1) constructs an intermediate domain consisting of fine-grained interchange signals from both source and target domains without destabilizing the semantic coherency of objects and background around the ego-vehicle; and 2) utilizes the intermediate domain for self-training.
no code implementations • 4 Aug 2021 • Lingdong Kong, Prakhar Ganesh, Tan Wang, Junhao Liu, Le Zhang, Yao Chen
We hope that the scale, diversity, and quality of our dataset can benefit researchers in this area and beyond.