# Rethinking Rotation-Invariant Recognition of Fine-grained Shapes from the Perspective of Contour Points

arXiv: https://arxiv.org/abs/2503.10992 · HTML: https://mlsanity.com/paper/2503.10992/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 64 references that are in the map.
- First posted on arXiv 14 Mar 2025.

## Builds on (most cited first, 22 of 22)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Group Equivariant Convolutional Networks](https://mlsanity.com/paper/1602.07576/) (2016)
- [General E(2)-Equivariant Steerable CNNs](https://mlsanity.com/paper/1911.08251/) (2019)
- [AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation](https://mlsanity.com/paper/2206.08023/) (2022)
- [Harmonic Networks: Deep Translation and Rotation Equivariance](https://mlsanity.com/paper/1612.04642/) (2016)
- [D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features](https://mlsanity.com/paper/2003.03164/) (2020)
- [Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptors](https://mlsanity.com/paper/2202.11660/) (2022)
- [Gabor Convolutional Networks](https://mlsanity.com/paper/1705.01450/) (2017)
- [Category-Level Metric Scale Object Shape and Pose Estimation](https://mlsanity.com/paper/2109.00326/) (2021)
- [Real-time Deep Pose Estimation with Geodesic Loss for Image-to-Template Rigid Registration](https://mlsanity.com/paper/1803.05982/) (2018)
- [Rotational Projection Statistics for 3D Local Surface Description and Object Recognition](https://mlsanity.com/paper/1304.3192/) (2013)
- [RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning](https://mlsanity.com/paper/2202.13094/) (2022)
- [R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Method](https://mlsanity.com/paper/2103.08129/) (2021)
- [RIC-CNN: Rotation-Invariant Coordinate Convolutional Neural Network](https://mlsanity.com/paper/2211.11812/) (2022)
- [The Devil is in the Pose: Ambiguity-free 3D Rotation-invariant Learning via Pose-aware Convolution](https://mlsanity.com/paper/2205.15210/) (2022)
- [Automatic registration with continuous pose updates for marker-less surgical navigation in spine surgery](https://mlsanity.com/paper/2308.02917/) (2023)
- [How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval?](https://mlsanity.com/paper/2403.07203/) (2024)
- [Understanding when spatial transformer networks do not support invariance, and what to do about it](https://mlsanity.com/paper/2004.11678/) (2020)
- [A novel joint points and silhouette-based method to estimate 3D human pose and shape](https://mlsanity.com/paper/2012.06109/) (2020)

## Abstract (arXiv)

Rotation-invariant recognition of shapes is a common challenge in computer vision. Recent approaches have significantly improved the accuracy of rotation-invariant recognition by encoding the rotational invariance of shapes as hand-crafted image features and introducing deep neural networks. However, the methods based on pixels have too much redundant information, and the critical geometric information is prone to early leakage, resulting in weak rotation-invariant recognition of fine-grained shapes. In this paper, we reconsider the shape recognition problem from the perspective of contour points rather than pixels. We propose an anti-noise rotation-invariant convolution module based on contour geometric aware for fine-grained shape recognition. The module divides the shape contour into multiple local geometric regions(LGA), where we implement finer-grained rotation-invariant coding in terms of point topological relations. We provide a deep network composed of five such cascaded modules for classification and retrieval experiments. The results show that our method exhibits excellent performance in rotation-invariant recognition of fine-grained shapes. In addition, we demonstrate that our method is robust to contour noise and the rotation centers. The source code is available at https://github.com/zhenguonie/ANRICN_CGA.