Three-Dimensional Object Detection and Layout Prediction Using Clouds of Oriented Gradients

By Zhile Ren, Erik B. Sudderth. 2016

153 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology

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

1. Charles Ruizhongtai Qi
2. Leonidas J. Guibas
3. Or Litany
4. Andreas Geiger
5. Hongsheng Li
6. Shaoshuai Shi
7. Raquel Urtasun
8. Binh Yang

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Xiaogang Wang
3. Jitendra Malik
4. Dacheng Tao
5. Ming-Hsuan Yang
6. Alan L. Yuille
7. Yi Yang
8. Trevor Darrell

In Geology

1. Charles Ruizhongtai Qi
2. Leonidas J. Guibas
3. Or Litany
4. Raquel Urtasun
5. Hongsheng Li
6. Shaoshuai Shi
7. Binh Yang
8. Ming Liang

Citations in the corpus

• Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images (2015, background): “Recently, [32] also proposed the Clouds of Oriented Gradients feature on RGB-D images.”
• SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation (2017, background): “Following these pioneering 2D works, 3D bounding box detection frameworks have emerged [38, 42, 43, 11, 5].”
• ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes (2020, methodology): “COG [37] is a sliding shape based detector using 3D HoG like feature extracted from RGB-D data.”
• Deep Hough Voting for 3D Object Detection in Point Clouds (2019, methodology): “Examples include: [27] where a pair-wise semantic context potential helps guide the proposals objectness score; template-based methods [26, 32, 28]; Sliding-shapes [41] and its deep learning-based successor [42]; Clouds of Oriented Gradi-ents (COG) [38]; and the recent 3D-SIS [12].”
• PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation (2017, methodology): “We report 3D detection performance of our models on the same 10 object categories as in [26, 16].”
• EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection (2020, result): “oach in the indoor scenes. Table 6 demonstrates the results compared with the state-of-the-art methods. Our EPNet achieves superior detection performance, outperforming PointFusion [37] by 15.7%, COG [30] by 12.2%, F-PointNet [27] by 5.8% and VoteNet [26] by 2.1% in terms of 3D mAP. The comparisons ”
• Multi-Task Multi-Sensor Fusion for 3D Object Detection (2019, background): “Other contextual cues such as the room layout [23, 26], and support surface [24] have also been exploited to help 3D object reasoning in the context of indoor scenes.”
• Accurate Monocular 3D Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving (2019, background): “LiDAR provides reliable depth information that can be used to accurately localize objects and characterize their shapes, many approaches [14, 19, 21, 27, 5, 33, 40] use LiDAR point clouds as their input, and get impressive detection results in autonomous driving scenarios.”
• Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal (2019, unknown): “ar, orange for pedestrian, and yellow for cyclist. Method bathtub bed bookshelf chair desk dresser nightstand soft table toilet mean DSS [21] 44.2 78.8 11.9 61.2 20.5 6.4 15.4 53.5 50.3 78.9 42.1 COG [29] 58.26 63.67 31.80 62.17 45.19 15.47 27.36 51.02 51.29 70.07 47.63 2Ddriven3D [30] 43.45 64.48 3”
• Frustum PointNets for 3D Object Detection from RGB-D Data (2017, background): “4% better 3D mAP than [13] and [24] on SUN-RGBD while running one to three orders of magnitude faster.”