1 code implementation • 31 Jul 2023 • Zhelun Shen, Xibin Song, Yuchao Dai, Dingfu Zhou, Zhibo Rao, Liangjun Zhang
Due to the domain differences and unbalanced disparity distribution across multiple datasets, current stereo matching approaches are commonly limited to a specific dataset and generalize poorly to others.
1 code implementation • 29 Jan 2023 • Jin Fang, Dingfu Zhou, Jingjing Zhao, Chenming Wu, Chulin Tang, Cheng-Zhong Xu, Liangjun Zhang
This setting results in two distinct domain gaps: scenarios and sensors, making it difficult to analyze and evaluate the method accurately.
1 code implementation • 26 Jul 2022 • Junbo Yin, Dingfu Zhou, Liangjun Zhang, Jin Fang, Cheng-Zhong Xu, Jianbing Shen, Wenguan Wang
Existing approaches for unsupervised point cloud pre-training are constrained to either scene-level or point/voxel-level instance discrimination.
1 code implementation • 26 Jul 2022 • Junbo Yin, Jin Fang, Dingfu Zhou, Liangjun Zhang, Cheng-Zhong Xu, Jianbing Shen, Wenguan Wang
To reduce the dependence on large supervision, semi-supervised learning (SSL) based approaches have been proposed.
2 code implementations • 4 Jul 2022 • Xuhong LI, Haoyi Xiong, Yi Liu, Dingfu Zhou, Zeyu Chen, Yaqing Wang, Dejing Dou
Though image classification datasets could provide the backbone networks with rich visual features and discriminative ability, they are incapable of fully pre-training the target model (i. e., backbone+segmentation modules) in an end-to-end manner.
no code implementations • 24 Mar 2022 • Zhiyuan Zhang, Jiadai Sun, Yuchao Dai, Dingfu Zhou, Xibin Song, Mingyi He
Existing correspondences-free methods generally learn the holistic representation of the entire point cloud, which is fragile for partial and noisy point clouds.
no code implementations • 28 Oct 2021 • Zhiyuan Zhang, Jiadai Sun, Yuchao Dai, Dingfu Zhou, Xibin Song, Mingyi He
Even though considerable progress has been made in deep learning-based 3D point cloud processing, how to obtain accurate correspondences for robust registration remains a major challenge because existing hard assignment methods cannot deal with outliers naturally.
1 code implementation • ICCV 2021 • Zongdai Liu, Dingfu Zhou, Feixiang Lu, Jin Fang, Liangjun Zhang
For generating the ground truth of 2D/3D keypoints, an automatic model-fitting approach has been proposed by fitting the deformed 3D object model and the object mask in the 2D image.
1 code implementation • 23 Jun 2021 • Shaoqing Xu, Dingfu Zhou, Jin Fang, Junbo Yin, Zhou Bin, Liangjun Zhang
Then the segmentation results from different sensors are adaptively fused based on the proposed attention-based semantic fusion module.
no code implementations • CVPR 2021 • Jin Fang, Xinxin Zuo, Dingfu Zhou, Shengze Jin, Sen Wang, Liangjun Zhang
Finally, we verify the proposed framework on the public KITTI dataset with different 3D object detectors.
no code implementations • 10 Mar 2021 • Jin Fang, Dingfu Zhou, Xibin Song, Liangjun Zhang
In this paper, we propose a simple but effective framework - MapFusion to integrate the map information into modern 3D object detector pipelines.
no code implementations • 5 Mar 2021 • Dingfu Zhou, Xibin Song, Yuchao Dai, Junbo Yin, Feixiang Lu, Jin Fang, Miao Liao, Liangjun Zhang
3D object detection from a single image is an important task in Autonomous Driving (AD), where various approaches have been proposed.
Ranked #19 on Monocular 3D Object Detection on KITTI Cars Moderate
2 code implementations • ECCV 2020 • Miao Liao, Feixiang Lu, Dingfu Zhou, Sibo Zhang, Wei Li, Ruigang Yang
To get clear street-view and photo-realistic simulation in autonomous driving, we present an automatic video inpainting algorithm that can remove traffic agents from videos and synthesize missing regions with the guidance of depth/point cloud.
Ranked #1 on Image Inpainting on ApolloScape
no code implementations • 16 Jul 2020 • Feixiang Lu, Zongdai Liu, Xibin Song, Dingfu Zhou, Wei Li, Hui Miao, Miao Liao, Liangjun Zhang, Bin Zhou, Ruigang Yang, Dinesh Manocha
We present a novel approach to detect, segment, and reconstruct complete textured 3D models of vehicles from a single image for autonomous driving.
2 code implementations • 23 Jun 2020 • Zhelun Shen, Yuchao Dai, Xibin Song, Zhibo Rao, Dingfu Zhou, Liangjun Zhang
First, we construct combination volumes on the upper levels of the pyramid and develop a cost volume fusion module to integrate them for initial disparity estimation.
no code implementations • CVPR 2020 • Xibin Song, Yuchao Dai, Dingfu Zhou, Liu Liu, Wei Li, Hongdng Li, Ruigang Yang
Second, we propose a new framework for real-world DSR, which consists of four modules : 1) An iterative residual learning module with deep supervision to learn effective high-frequency components of depth maps in a coarse-to-fine manner; 2) A channel attention strategy to enhance channels with abundant high-frequency components; 3) A multi-stage fusion module to effectively re-exploit the results in the coarse-to-fine process; and 4) A depth refinement module to improve the depth map by TGV regularization and input loss.
no code implementations • CVPR 2020 • Dingfu Zhou, Jin Fang, Xibin Song, Liu Liu, Junbo Yin, Yuchao Dai, Hongdong Li, Ruigang Yang
To tackle this problem, we propose a simple but practical detection framework to jointly predict the 3D BBox and instance segmentation.
Ranked #11 on 3D Object Detection on KITTI Cars Hard
1 code implementation • CVPR 2020 • Junbo Yin, Jianbing Shen, Chenye Guan, Dingfu Zhou, Ruigang Yang
In this paper, we propose an end-to-end online 3D video object detector that operates on point cloud sequences.
1 code implementation • 15 Mar 2020 • Liu Liu, Dylan Campbell, Hongdong Li, Dingfu Zhou, Xibin Song, Ruigang Yang
Conventional absolute camera pose via a Perspective-n-Point (PnP) solver often assumes that the correspondences between 2D image pixels and 3D points are given.
1 code implementation • 11 Aug 2019 • Dingfu Zhou, Jin Fang, Xibin Song, Chenye Guan, Junbo Yin, Yuchao Dai, Ruigang Yang
In 2D/3D object detection task, Intersection-over-Union (IoU) has been widely employed as an evaluation metric to evaluate the performance of different detectors in the testing stage.
no code implementations • 3 Mar 2019 • Dingfu Zhou, Yuchao Dai, Hongdong Li
Recovering the absolute metric scale from a monocular camera is a challenging but highly desirable problem for monocular camera-based systems.
no code implementations • CVPR 2019 • Xibin Song, Peng Wang, Dingfu Zhou, Rui Zhu, Chenye Guan, Yuchao Dai, Hao Su, Hongdong Li, Ruigang Yang
Specifically, we first segment each car with a pre-trained Mask R-CNN, and then regress towards its 3D pose and shape based on a deformable 3D car model with or without using semantic keypoints.
no code implementations • 17 Nov 2018 • Jin Fang, Dingfu Zhou, Feilong Yan, Tongtong Zhao, Feihu Zhang, Yu Ma, Liang Wang, Ruigang Yang
Instead, we can simply deploy a vehicle with a LiDAR scanner to sweep the street of interests to obtain the background point cloud, based on which annotated point cloud can be automatically generated.
1 code implementation • 8 Sep 2018 • Yan Xia, Yang Zhang, Dingfu Zhou, Xinyu Huang, Cheng Wang, Ruigang Yang
Then, the image together with the retrieved shape model is fed into the proposed network to generate the fine-grained 3D point cloud.
2 code implementations • 16 Mar 2018 • Xinyu Huang, Peng Wang, Xinjing Cheng, Dingfu Zhou, Qichuan Geng, Ruigang Yang
In this paper, we provide a sensor fusion scheme integrating camera videos, consumer-grade motion sensors (GPS/IMU), and a 3D semantic map in order to achieve robust self-localization and semantic segmentation for autonomous driving.
no code implementations • 12 Jul 2017 • Dingfu Zhou, Yuchao Dai, Hongdong Li
First, we prove that there indeed exist enough degrees of freedom to apply pixel-wise local homography for stereo rectification.