2 code implementations • 20 Jun 2022 • Chen Min, Xinli Xu, Dawei Zhao, Liang Xiao, Yiming Nie, Bin Dai
This work proposes a solution to reduce the dependence on labelled 3D training data by leveraging pre-training on large-scale unlabeled outdoor LiDAR point clouds using masked autoencoders (MAE).
2 code implementations • 30 May 2023 • Chen Min, Liang Xiao, Dawei Zhao, Yiming Nie, Bin Dai
When compared to monocular pre-training methods on the nuScenes dataset, UniScene shows a significant improvement of about 2. 0% in mAP and 2. 0% in NDS for multi-camera 3D object detection, as well as a 3% increase in mIoU for surrounding semantic scene completion.
1 code implementation • 6 Apr 2021 • Chen Min, Jiaolong Xu, Liang Xiao, Dawei Zhao, Yiming Nie, Bin Dai
Deep learning has recently demonstrated its promising performance for vision-based parking-slot detection.
2 code implementations • 20 Jun 2022 • Chen Min, Weizhong Jiang, Dawei Zhao, Jiaolong Xu, Liang Xiao, Yiming Nie, Bin Dai
Freespace detection is an essential component of autonomous driving technology and plays an important role in trajectory planning.
1 code implementation • ICCV 2021 • Zizhuang Wei, Qingtian Zhu, Chen Min, Yisong Chen, Guoping Wang
To overcome the difficulty of varying occlusion in complex scenes, we propose an inter-view cost volume aggregation module for adaptive pixel-wise view aggregation, which is able to preserve better-matched pairs among all views.
Ranked #10 on Point Clouds on Tanks and Temples (Mean F1 (Intermediate) metric)
1 code implementation • 14 Aug 2023 • Chen Min, Dawei Zhao, Liang Xiao, Yiming Nie, Bin Dai
In this paper, we draw inspiration from Alberto Elfes' pioneering work in 1989, where he introduced the concept of the occupancy grid as World Models for robots.
no code implementations • 29 Aug 2018 • Chen Min, Hao Yixue, Lin Kai, Yuan Zhiyong, Hu Long
In order to solve this problem, we design a traffic control algorithm based on label-less learning on the edge cloud, which is dubbed as LLTC.
no code implementations • 18 Jun 2021 • Qingtian Zhu, Chen Min, Zizhuang Wei, Yisong Chen, Guoping Wang
3D reconstruction has lately attracted increasing attention due to its wide application in many areas, such as autonomous driving, robotics and virtual reality.
no code implementations • 22 Aug 2022 • Zengran Wang, Chen Min, Zheng Ge, Yinhao Li, Zeming Li, Hongyu Yang, Di Huang
Instead of using a sole monocular depth method, in this work, we propose a novel Surround-view Temporal Stereo (STS) technique that leverages the geometry correspondence between frames across time to facilitate accurate depth learning.
no code implementations • 8 Apr 2024 • Qinglu Min, Jie Zhao, Zhihao Zhang, Chen Min
Deep learning has recently demonstrated its excellent performance on the task of multi-view stereo (MVS).