3D Object Proposals for Accurate Object Class Detection

By Xiaozhi Chen, Kaustav Kundu, Yukun Zhu, Andrew G. Berneshawi, Huimin Ma, Sanja Fidler, Raquel Urtasun. 2015

904 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

Objects as Points (2019, methodology): “KITTI contains 7841 training images and we follow standard training and validation splits in literature [10, 54].”
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size (2016, methodology): “ImageNettrained DNNs have also been applied to a number of applications pertaining to autonomous driving, including pedestrian and vehicle detection in images [12, 7] and videos [2], as well as segmenting the shape of the road [1].”
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection (2017, methodology): “Here, we aim to directly estimate the oriented 3D box and normalize Δx and Δy homogeneously with the diagonal d, which is different from [34, 40, 22, 21, 4, 3, 5].”
3D fully convolutional network for vehicle detection in point cloud (2016, methodology): “[4], [20] propose to detect objects from the RGBD representation captured by Kinect alike sensor.”
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].”
Vehicle Detection from 3D Lidar Using Fully Convolutional Network (2016, background): “We would also like to mention that object detection on RGBD images [3, 17] is closely related to the topic of object detection on range scan.”
Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images (2015, background): “For 3D object proposals, [4] introduces an MRF formulation with hand-crafted features for a few object categories in street scenes.”
A Survey of Autonomous Driving: Common Practices and Emerging Technologies (2019, methodology): “point cloud data in 2D, the first being a so-called depth image shown in Figure 14, largely inspired by camera-based methods that perform 3D object detection through depth estimation [165] and methods that operate on RGB-D data [166].”
Understanding the Effective Receptive Field in Deep Convolutional Neural Networks (2016, positive): “In this paper we focus on their application to computer vision: where they are the driving force behind the significant improvement of the state-of-the-art for many tasks recently, including image recognition [10, 8], object detection [17, 2], semantic segmentation [12, 1], image captioning [20], an”
nuScenes: A Multimodal Dataset for Autonomous Driving (2019, background): “However, 3D localization from images is challenging [13, 12, 57, 80, 69, 66, 73].”
Pyramid Stereo Matching Network (2018, neutral): “Depth estimation from stereo images is essential to computer vision applications, including autonomous driving for vehicles, 3D model reconstruction, and object detection and recognition [4, 31].”
Adapting Object Detectors with Conditional Domain Normalization (2020, positive): “ve been developed like Fast RCNN [10], Faster R-CNN [33], and Mask R-CNN [12], which signicantly push forward the state of the art. In 3D detection, spanning from detecting 3d objects from 2d images [3], to directly generate 3D box from point cloud [30, 38], abundant works has been successfully expl”
PointPillars: Fast Encoders for Object Detection From Point Clouds (2018, methodology): “For experimental studies we split the official training set into 3712 training samples and 3769 validation samples [1], while for our test submission we created a mini-val set of 784 samples from the validation set and trained on the remaining 6733 samples.”
FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds (2017, background): “Applications of learning on point clouds include shape completion and recognition [54], unmanned autonomous vehicles [34], 3D object detection, recognition and classification [9, 31, 38, 39, 45, 46, 50], contour detection [20], layout inference [16], scene labeling [29], category discovery [57], poi”
Objects are Different: Flexible Monocular 3D Object Detection (2021, methodology): “We follow [9] to split the training images into train (3712) and val (3769) sets.”
A General Pipeline for 3D Detection of Vehicles (2018, methodology): “Following [36], we split the training/validation set into training and validation sub-sets.”