Monocular 3D Object Detection for Autonomous Driving

By Xiaozhi Chen, Kaustav Kundu, Ziyu Zhang, Huimin Ma, Sanja Fidler, Raquel Urtasun. 2016

1,014 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Objects as Points (2019, methodology): “We compare with slow-RCNN based Deep3DBox [38] and Faster-RCNN based method Mono3D [9], on their spe-ciﬁc validation split.”
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection (2017, methodology): “The split avoids samples from the same sequence being included in both the training and the validation set [3].”
A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation (2016, positive): “The semantic consistency loss is added for the outdoor scenario, with a semantic segmentation network trained using the DeepLab model (Chen et al., 2016).”
Multi-view 3D Object Detection Network for Autonomous Driving (2016, methodology): “As expected, all LIDAR-based approaches performs better than stereo-based method 3DOP [4] and monocular method Mono3D [3].”
Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detection (2018, background): “Deep learning has been introduced to object detection in the autonomous driving settings that use cameras [1]–[3], Lidar [4]–[10], or both [11]–[17], and has set the benchmark on many popular datasets (e.”
nuScenes: A Multimodal Dataset for Autonomous Driving (2019, background): “However, 3D localization from images is challenging [13, 12, 57, 80, 69, 66, 73].”
PIXOR: Real-time 3D Object Detection from Point Clouds (2018, methodology): “Camera based approaches utilize either monocular [1] or stereo images [2].”
RT3D: Real-Time 3-D Vehicle Detection in LiDAR Point Cloud for Autonomous Driving (2018, methodology): “comparison to Mono3D [17], 3DOP [8], and MV3D [9],”
M3D-RPN: Monocular 3D Region Proposal Network for Object Detection (2019, methodology): “64) on the moderate and hard settings despite being trained as a shared multi-class model and compared to single model methods [7,8, 28,40].”
RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving (2020, methodology): “In comparison, monocular camera devices are cheaper and convenient which makes it drawing an increasing attention in many application scenarios [7, 28, 42].”
PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud (2018, background): “[2, 3] formulated the 3D geometric information of objects as an energy function to score the predefined 3D boxes.”
Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving (2019, neutral): “…pipeline (Ren et al., 2015; He et al., 2017; Lin et al., 2017) — fell far behind in localizing objects in 3D (Li et al., 2019a; Xiang et al., 2015; 2017; Chabot et al., 2017; Mousavian et al., 2017; Chen et al., 2015; Xu & Chen, 2018; Chen et al., 2016; Pham & Jeon, 2017; Chen et al., 2018)3.”
Multi-level Fusion Based 3D Object Detection from Monocular Images (2018, methodology): “Here three methods are chosen for comparisons: Mono3D [2], 3DOP [3] and Deep3DBox [26].”
SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation (2020, methodology): “Note that as pointed out by [31], the Method 2D Object Detection Easy Moderate Hard Mono3D[3] 94.”
Joint 3D Proposal Generation and Object Detection from View Aggregation (2017, methodology): “Recall: 3D proposal generation is evaluated using 3D bounding box recall at a 0:5 3D IoU threshold. We compare three variants of our RPN against the proposal generation algorithms 3DOP [6] and Mono3D [7]. Fig. 5 shows the recall vs number of proposals curves for our RPN varients, 3DOP and Mono3D. It”
Delving into Localization Errors for Monocular 3D Object Detection (2021, methodology): “Since the ground truth for the test set is not available and the access to the test server is limited, we follow the protocol of prior works [6, 7, 8] to divide the training data into a training set (3,712 images) and a validation set (3,769 images).”
3D Bounding Box Estimation Using Deep Learning and Geometry (2016, methodology): “In more restrictive driving scenarios alternatives to full 3D pose estimation explore exhaustive sampling and scoring of all hypotheses [4] using a variety of contextual and semantic cues.”
Complex-YOLO: An Euler-Region-Proposal for Real-Time 3D Object Detection on Point Clouds (2018, background): “In general, object detection and classification based on deep learning is a well known task and widely established for 2D bounding box regression on images [12] [13] [14] [15] [16] [17] [18] [19] [20] [21].”
IoU Loss for 2D/3D Object Detection (2019, background): “birdeye-view [17] or front-view [18]) to obtained the 2D detection and then re-project the 2D Bbox into 3D to get the finally results.”
Complex-YOLO: Real-time 3D Object Detection on Point Clouds (2018, background): “ons [10] [11]. In general, object detection and classication based on deep learning is a well known task and widely established for 2D bounding box regression on images [12] [13] [14] [15] [16] [17] [18] [19] [20] [21]. Research focus was mainly a tradeo between accuracy and eciency. In regard to au”