mlsanityData to 14 Oct 2026

Sim2Real 3D Object Classification using Spherical Kernel Point Convolution and a Deep Center Voting Scheme

arXiv 2103.06134 ↗First posted 10 Mar 2021cs.CV cs.ROcited by 1

Not on the map. Why?

Abstract (arXiv)

While object semantic understanding is essential for most service robotic tasks, 3D object classification is still an open problem. Learning from artificial 3D models alleviates the cost of annotation necessary to approach this problem, but most methods still struggle with the differences existing between artificial and real 3D data. We conjecture that the cause of those issue is the fact that many methods learn directly from point coordinates, instead of the shape, as the former is hard to center and to scale under variable occlusions reliably. We introduce spherical kernel point convolutions that directly exploit the object surface, represented as a graph, and a voting scheme to limit the impact of poor segmentation on the classification results. Our proposed approach improves upon state-of-the-art methods by up to 36% when transferring from artificial objects to real objects.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 14 of its 21 references that are in the map. First posted on arXiv 10 Mar 2021.

Builds on

14 of 21 references.

References · 14

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  8. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  9. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  10. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  11. 2019SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operatorcited by 89
  12. 2020Rotation-Invariant Point Convolution With Multiple Equivariant Alignmentscited by 7
2 more
  1. 2018Noise-resistant Deep Learning for Object Classification in 3D Point Clouds Using a Point Pair Descriptorcited by 2
  2. 2019Addressing the Sim2Real Gap in Robotic 3D Object Classificationcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understandingcited by 184