CAD-model recognition and 6DOF pose estimation using 3D cues

By Aitor Aldoma, Markus Vincze, Nico Blodow, David Gossow, Suat Gedikli, Radu Bogdan Rusu, Gary R. Bradski. IEEE International Conference on Computer Vision, 2011

335 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/9d6fe168ce4c3bb69c9b3bb75dc9721a228c82bc

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. Matthias Nießner
2. Federico Tombari
3. Angela Dai
4. Leonidas J. Guibas
5. Luigi Di Stefano
6. Markus Vincze
7. Aitor Aldoma
8. Walter Wohlkinger

In Computer Vision and Pattern Recognition

1. Matthias Nießner
2. Federico Tombari
3. Luc Van Gool
4. Leonidas J. Guibas
5. Vladlen Koltun
6. Jitendra Malik
7. Kristen Grauman
8. Xiaogang Wang

In Geology

1. Matthias Nießner
2. Angela Dai
3. Federico Tombari
4. Leonidas J. Guibas
5. Markus Vincze
6. Luigi Di Stefano
7. Aitor Aldoma
8. Walter Wohlkinger

Citations in the corpus

• LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis (2018, methodology): “n and loop closure detection tasks, to facilitate relevant robotics and self-driving applications. 2. Related Work Most existing solutions for acquiring point cloud features are achieved by handcraft [17, 1, 8], but they are usually tailored to specific tasks and therefore have poor generalization fe”
• 3DNet: Large-scale object class recognition from CAD models (2012, methodology): “2) CVFH: The Clustered Viewpoint Feature His-togram [1] is a semi-global view based descriptor based on VFH.”
• M2DP: A novel 3D point cloud descriptor and its application in loop closure detection (2016, background): “Then, CVFH uses the region’s average normal and centroid to compute the VFH descriptor.”
• Supervised learning of hidden and non-hidden 0-order affordances and detection in real scenes (2012, background): “Moreover, combined with the Camera’s Roll Histogram (CRH) [25], aimed at determining the final degree of freedom over the camera axis and a post-processing step, it is able to accurately determine the object poses.”
• Ensemble of shape functions for 3D object classification (2011, neutral): “• CVFH: The Clustered Viewpoint Feature Histogram [1] is a semi-global view based descriptor based on VFH.”
• GDRNPP: A Geometry-Guided and Fully Learning-Based Object Pose Estimator (2021, neutral): “In the pre-deep learning era, methods can be roughly categorized into feature-based [8], [9], [10] and template-based [11], [12], [13] approaches.”
• Database‐Assisted Object Retrieval for Real‐Time 3D Reconstruction (2015, background): “Thus, a natural extension is the consideration of larger support features; i.e., defining descriptors on regions which are based on clustering 3D points or planes [GG04, AVB ∗ 11, MPM ∗ 14].”
• A Global Hypotheses Verification Method for 3D Object Recognition (2012, methodology): “, [9, 10], compute a single descriptor which encompasses the whole object shape: this requires, in presence of clutter and/or occlusions, the scene to be pre-processed by a suitable 3D segmentation algorithm capable of extracting the individual object instances.”