1 code implementation • Under review for Transaction 2024 • Mu Hu, Wei Yin, Chi Zhang, Zhipeng Cai, Xiaoxiao Long, Hao Chen, Kaixuan Wang, Gang Yu, Chunhua Shen, Shaojie Shen
For metric depth estimation, we show that the key to a zero-shot single-view model lies in resolving the metric ambiguity from various camera models and large-scale data training.
Ranked #1 on Surface Normals Estimation on NYU Depth v2 (using extra training data)
no code implementations • 18 Mar 2024 • Guiyong Zheng, Jinqi Jiang, Chen Feng, Shaojie Shen, Boyu Zhou
To bridge this research gap, we propose MASSTAR: a Multi-modal lArge-scale Scene dataset with a verSatile Toolchain for surfAce pRediction and completion.
no code implementations • 18 Mar 2024 • Xiao Fu, Wei Yin, Mu Hu, Kaixuan Wang, Yuexin Ma, Ping Tan, Shaojie Shen, Dahua Lin, Xiaoxiao Long
We introduce GeoWizard, a new generative foundation model designed for estimating geometric attributes, e. g., depth and normals, from single images.
no code implementations • 7 Feb 2024 • Chuhao Liu, Ke Wang, Jieqi Shi, Zhijian Qiao, Shaojie Shen
Our method achieves 40. 3 mean average precision (mAP) on the ScanNet semantic instance segmentation task.
1 code implementation • 4 Feb 2024 • Lu Zhang, Peiliang Li, Sikang Liu, Shaojie Shen
This paper presents a Simple and effIcient Motion Prediction baseLine (SIMPL) for autonomous vehicles.
2 code implementations • 22 Aug 2023 • Zhijian Qiao, Zehuan Yu, Binqian Jiang, Huan Yin, Shaojie Shen
Utilizing these GEMs, we present a distrust-and-verify scheme based on a Pyramid Compatibility Graph for Global Registration (PAGOR).
no code implementations • 20 Aug 2023 • Chen Feng, Hangning Zhou, Huadong Lin, Zhigang Zhang, Ziyao Xu, Chi Zhang, Boyu Zhou, Shaojie Shen
Predicting the future behavior of agents is a fundamental task in autonomous vehicle domains.
2 code implementations • 22 Jul 2023 • Zhijian Qiao, Zehuan Yu, Huan Yin, Shaojie Shen
In this paper, we propose a graph-theoretic framework to address the problem of global point cloud registration with low overlap.
no code implementations • ICCV 2023 • Yiyao Zhu, Di Luan, Shaojie Shen
Predicting future trajectories of surrounding agents is essential for safety-critical autonomous driving.
no code implementations • 24 May 2023 • Chuhao Liu, Shaojie Shen
The current semantic-aided loop detection embeds the topology between semantic instances to search a loop.
no code implementations • 7 Mar 2023 • Pengqin Wang, Meixin Zhu, Shaojie Shen
It models the probability distribution of the environment dynamics and reward function to capture aleatoric uncertainty and treats epistemic uncertainty as a learnable noise parameter.
no code implementations • 3 Mar 2023 • Jieqi Shi, Peiliang Li, Xiaozhi Chen, Shaojie Shen
In this paper, we propose a quality evaluation network to score the point clouds and help judge the quality of the point cloud before applying the completion model.
1 code implementation • 13 Feb 2023 • Binqian Jiang, Shaojie Shen
This paper proposes \textit{Contour Context}, a simple, effective, and efficient topological loop closure detection pipeline with accurate 3-DoF metric pose estimation, targeting the urban utonomous driving scenario.
1 code implementation • 8 Feb 2023 • Jun Cen, Di Luan, Shiwei Zhang, Yixuan Pei, Yingya Zhang, Deli Zhao, Shaojie Shen, Qifeng Chen
Recently, Unified Open-set Recognition (UOSR) has been proposed to reject not only unknown samples but also known but wrongly classified samples, which tends to be more practical in real-world applications.
no code implementations • 17 Nov 2022 • Jieqi Shi, Peiliang Li, Xiaozhi Chen, Shaojie Shen
The image-based 3D object detection task expects that the predicted 3D bounding box has a ``tightness'' projection (also referred to as cuboid), which fits the object contour well on the image while still keeping the geometric attribute on the 3D space, e. g., physical dimension, pairwise orthogonal, etc.
no code implementations • 7 Feb 2022 • Jieqi Shi, Lingyun Xu, Peiliang Li, Xiaozhi Chen, Shaojie Shen
With the help of gated recovery units(GRU) and attention mechanisms as temporal units, we propose a point cloud completion framework that accepts a sequence of unaligned and sparse inputs, and outputs consistent and aligned point clouds.
no code implementations • 11 Nov 2021 • Jieqi Shi, Lingyun Xu, Liang Heng, Shaojie Shen
In this paper, we propose a Graph-Guided Deformation Network, which respectively regards the input data and intermediate generation as controlling and supporting points, and models the optimization guided by a graph convolutional network(GCN) for the point cloud completion task.
no code implementations • 5 Nov 2021 • Xiuyuan Lu, Yi Zhou, Shaojie Shen
In this paper, we present a cascaded two-level multi-model fitting method for identifying independently moving objects (i. e., the motion segmentation problem) with a monocular event camera.
1 code implementation • 2 Nov 2021 • Lu Zhang, Peiliang Li, Jing Chen, Shaojie Shen
In this paper, we present a graph-based trajectory prediction network named the Dual Scale Predictor (DSP), which encodes both the static and dynamical driving context in a hierarchical manner.
1 code implementation • 16 Dec 2020 • Yi Zhou, Guillermo Gallego, Xiuyuan Lu, SiQi Liu, Shaojie Shen
We develop a method to identify independently moving objects acquired with an event-based camera, i. e., to solve the event-based motion segmentation problem.
no code implementations • 20 Oct 2020 • Jieqi Shi, Peiliang Li, Shaojie Shen
A robust 3D object tracker which continuously tracks surrounding objects and estimates their trajectories is key for self-driving vehicles.
no code implementations • 5 Aug 2020 • Chuhao Liu, Shaojie Shen
In this work, we build an AR interface that displays the reconstructed 3D map from the drone on physical surfaces in front of the operator.
Human-Computer Interaction Robotics
3 code implementations • 30 Jul 2020 • Yi Zhou, Guillermo Gallego, Shaojie Shen
We present a solution to the problem of visual odometry from the data acquired by a stereo event-based camera rig.
1 code implementation • 6 Jul 2020 • Boyu Zhou, Jie Pan, Fei Gao, Shaojie Shen
In this paper, we present RAPTOR, a robust and perception-aware replanning framework to support fast and safe flight.
Robotics
no code implementations • 5 Jun 2020 • Jieru Zhao, Tingyuan Liang, Liang Feng, Wenchao Ding, Sharad Sinha, Wei zhang, Shaojie Shen
To reduce the design effort and achieve the right balance, we propose FP-Stereo for building high-performance stereo matching pipelines on FPGAs automatically.
no code implementations • CVPR 2020 • Peiliang Li, Jieqi Shi, Shaojie Shen
Directly learning multiple 3D objects motion from sequential images is difficult, while the geometric bundle adjustment lacks the ability to localize the invisible object centroid.
1 code implementation • ECCV 2020 • Haoran Song, Wenchao Ding, Yuxuan Chen, Shaojie Shen, Michael Yu Wang, Qifeng Chen
Moreover, our approach enables a novel pipeline which couples the prediction and planning, by conditioning PiP on multiple candidate trajectories of the ego vehicle, which is highly beneficial for autonomous driving in interactive scenarios.
2 code implementations • 5 Mar 2020 • Lu Zhang, Wenchao Ding, Jing Chen, Shaojie Shen
Decision-making in dense traffic scenarios is challenging for automated vehicles (AVs) due to potentially stochastic behaviors of other traffic participants and perception uncertainties (e. g., tracking noise and prediction errors, etc.).
Robotics
2 code implementations • 29 Dec 2019 • Boyu Zhou, Fei Gao, Jie Pan, Shaojie Shen
A path-guided optimization (PGO) approach is devised to tackle infeasible local minima, which improves the replanning success rate significantly.
Robotics
1 code implementation • 12 Sep 2019 • Kaixuan Wang, Shaojie Shen
Third, beyond two-view depth estimation, we further extend the above networks to fuse depth information from multiple target images and estimate the depth map of the source image.
no code implementations • 11 Sep 2019 • Peiliang Li, Si-Qi Liu, Shaojie Shen
We propose a 3D object detection system with multi-sensor refinement in the context of autonomous driving.
1 code implementation • 10 Sep 2019 • Kaixuan Wang, Fei Gao, Shaojie Shen
First, superpixels extracted from both intensity and depth images are used to model surfels in the system.
2 code implementations • 24 Jun 2019 • Wenchao Ding, Lu Zhang, Jing Chen, Shaojie Shen
Planning safe trajectories for autonomous vehicles in complex urban environments is challenging since there are numerous semantic elements (such as dynamic agents, traffic lights and speed limits) to consider.
no code implementations • 24 Jun 2019 • Wenchao Ding, Wenliang Gao, Kaixuan Wang, Shaojie Shen
Our framework starts with an efficient B-spline-based kinodynamic (EBK) search algorithm which finds a feasible trajectory with minimum control effort and time.
3 code implementations • 15 Apr 2019 • Manohar Kuse, Shaojie Shen
Finally, we present the fully functional system with relative computation andhandling of multiple world co-ordinate system which is able to reduce odometry drift, recover fromcomplicated kidnap scenarios and random odometry failures.
Robotics
no code implementations • 12 Apr 2019 • Rui Fan, Jianhao Jiao, Jie Pan, Huaiyang Huang, Shaojie Shen, Ming Liu
This makes the damaged road areas more distinguishable from the road surface.
no code implementations • 26 Mar 2019 • Yonggen Ling, Kaixuan Wang, Shaojie Shen
This paper presents a probabilistic approach for online dense reconstruction using a single monocular camera moving through the environment.
Robotics
1 code implementation • 21 Mar 2019 • Jiarong Lin, Luqi Wang, Fei Gao, Shaojie Shen, Fu Zhang
To this end, we propose an end-to-end policy network, which imitates from the traditional pipeline and is fine-tuned using reinforcement learning.
Robotics
2 code implementations • 6 Mar 2019 • Luxin Han, Fei Gao, Boyu Zhou, Shaojie Shen
We integrate FIESTA into a completed quadrotor system and validate it by both simulation and onboard experiments.
Robotics
no code implementations • 3 Mar 2019 • Wenchao Ding, Shaojie Shen
In this paper, we present an online two-level vehicle trajectory prediction framework for urban autonomous driving where there are complex contextual factors, such as lane geometries, road constructions, traffic regulations and moving agents.
no code implementations • 3 Mar 2019 • Wenchao Ding, Jing Chen, Shaojie Shen
In this paper, we uncover that clues to vehicle behaviors over an extended horizon can be found in vehicle interaction, which makes it possible to anticipate the likelihood of a certain behavior, even in the absence of any clear maneuver pattern.
4 code implementations • CVPR 2019 • Peiliang Li, Xiaozhi Chen, Shaojie Shen
Our method, called Stereo R-CNN, extends Faster R-CNN for stereo inputs to simultaneously detect and associate object in left and right images.
3D Object Detection From Stereo Images Autonomous Driving +3
4 code implementations • 11 Jan 2019 • Tong Qin, Shaozu Cao, Jie Pan, Shaojie Shen
We highlight that our system is a general framework, which can easily fuse various global sensors in a unified pose graph optimization.
4 code implementations • 11 Jan 2019 • Tong Qin, Jie Pan, Shaozu Cao, Shaojie Shen
We validate the performance of our system on public datasets and through real-world experiments with multiple sensors.
no code implementations • 21 Aug 2018 • Kejie Qiu, Tong Qin, Hongwen Xie, Shaojie Shen
By introducing an additional constraint in the time domain, our monocular visual-inertial tracking system can obtain continuous six degree of freedom (6-DoF) pose estimation without scale ambiguity.
1 code implementation • 2 Aug 2018 • Tong Qin, Shaojie Shen
Visual and inertial fusion is a popular technology for 6-DOF state estimation in recent years.
1 code implementation • 23 Jul 2018 • Kaixuan Wang, Shaojie Shen
In this paper, we present MVDepthNet, a convolutional network to solve the depth estimation problem given several image-pose pairs from a localized monocular camera in neighbor viewpoints.
no code implementations • ECCV 2018 • Peiliang Li, Tong Qin, Shaojie Shen
We propose a stereo vision-based approach for tracking the camera ego-motion and 3D semantic objects in dynamic autonomous driving scenarios.
1 code implementation • 5 Mar 2018 • Tong Qin, Perliang Li, Shaojie Shen
In this paper, we propose a monocular visual-inertial SLAM system, which can relocalize camera and get the absolute pose in a previous-built map.
no code implementations • 24 Sep 2017 • Siyi Li, Tianbo Liu, Chi Zhang, Dit-yan Yeung, Shaojie Shen
While deep reinforcement learning (RL) methods have achieved unprecedented successes in a range of challenging problems, their applicability has been mainly limited to simulation or game domains due to the high sample complexity of the trial-and-error learning process.
11 code implementations • 13 Aug 2017 • Tong Qin, Peiliang Li, Shaojie Shen
A monocular visual-inertial system (VINS), consisting of a camera and a low-cost inertial measurement unit (IMU), forms the minimum sensor suite for metric six degrees-of-freedom (DOF) state estimation.
Robotics