mlsanityData to 7 Oct 2026

Evaluating 3D Shape Analysis Methods for Robustness to Rotation Invariance

arXiv 2305.18557 ↗First posted 29 May 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper analyzes the robustness of recent 3D shape descriptors to SO(3) rotations, something that is fundamental to shape modeling. Specifically, we formulate the task of rotated 3D object instance detection. To do so, we consider a database of 3D indoor scenes, where objects occur in different orientations. We benchmark different methods for feature extraction and classification in the context of this task. We systematically contrast different choices in a variety of experimental settings investigating the impact on the performance of different rotation distributions, different degrees of partial observations on the object, and the different levels of difficulty of negative pairs. Our study, on a synthetic dataset of 3D scenes where objects instances occur in different orientations, reveals that deep learning-based rotation invariant methods are effective for relatively easy settings with easy-to-distinguish pairs. However, their performance decreases significantly when the difference in rotations on the input pair is large, or when the degree of observation of input objects is reduced, or the difficulty level of input pair is increased. Finally, we connect feature encodings designed for rotation-invariant methods to 3D geometry that enable them to acquire the property of rotation invariance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 49 references that are in the map. First posted on arXiv 29 May 2023.

Builds on

27 of 49 references.

References · 27

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  6. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  7. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  8. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  9. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  10. 2018Spherical CNNscited by 452
  11. 20203D-FRONT: 3D Furnished Rooms with layOuts and semaNTicscited by 375
  12. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
15 more
  1. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  2. 2018PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptorscited by 140
  3. 2019Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 80
  4. 2020A Rotation-Invariant Framework for Deep Point Cloud Analysiscited by 62
  5. 2018Learning Descriptor Networks for 3D Shape Synthesis and Analysiscited by 56
  6. 2019Deep Level Sets: Implicit Surface Representations for 3D Shape Inferencecited by 52
  7. 2018View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictionscited by 43
  8. 2019Quaternion Equivariant Capsule Networks for 3D Point Cloudscited by 41
  9. 2019SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentationcited by 29
  10. 2022RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 29
  11. 2017GRASS: Generative Recursive Autoencoders for Shape Structurescited by 24
  12. 2022The Devil is in the Pose: Ambiguity-free 3D Rotation-invariant Learning via Pose-aware Convolutioncited by 18
  13. 2021PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Featurescited by 15
  14. 2022ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotationcited by 12
  15. 2019Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topologycited by 11

Built on by

Not cited yet.