# Fine-Grained 3D Shape Classification with Hierarchical Part-View Attentions

arXiv: https://arxiv.org/abs/2005.12541 · HTML: https://mlsanity.com/paper/2005.12541/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2020.

## Built on by (most cited first, 30 of 30)

- [SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer](https://mlsanity.com/paper/2108.04444/) (2021)
- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Paths](https://mlsanity.com/paper/2202.09507/) (2022)
- [Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding](https://mlsanity.com/paper/2103.07838/) (2021)
- [Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer](https://mlsanity.com/paper/2202.09367/) (2022)
- [Fast Learning Radiance Fields by Shooting Much Fewer Rays](https://mlsanity.com/paper/2208.06821/) (2022)
- [MedShapeNet -- A Large-Scale Dataset of 3D Medical Shapes for Computer Vision](https://mlsanity.com/paper/2308.16139/) (2023)
- [Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matching](https://mlsanity.com/paper/2108.03746/) (2021)
- [Make-A-Shape: a Ten-Million-scale 3D Shape Model](https://mlsanity.com/paper/2401.11067/) (2024)
- [Learning a Structured Latent Space for Unsupervised Point Cloud Completion](https://mlsanity.com/paper/2203.15580/) (2022)
- [Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodings](https://mlsanity.com/paper/2411.08017/) (2024)
- [Towards Controllable Diffusion Models via Reward-Guided Exploration](https://mlsanity.com/paper/2304.07132/) (2023)
- [Hierarchical View Predictor: Unsupervised 3D Global Feature Learning through Hierarchical Prediction among Unordered Views](https://mlsanity.com/paper/2108.03743/) (2021)
- [Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2308.09314/) (2023)
- [RISurConv: Rotation Invariant Surface Attention-Augmented Convolutions for 3D Point Cloud Classification and Segmentation](https://mlsanity.com/paper/2408.06110/) (2024)
- [APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Classification](https://mlsanity.com/paper/2205.00847/) (2022)
- [MXM-CLR: A Unified Framework for Contrastive Learning of Multifold Cross-Modal Representations](https://mlsanity.com/paper/2303.10839/) (2023)
- [Semantic-Aware Implicit Template Learning via Part Deformation Consistency](https://mlsanity.com/paper/2308.11916/) (2023)
- [Dual Pose-invariant Embeddings: Learning Category and Object-specific Discriminative Representations for Recognition and Retrieval](https://mlsanity.com/paper/2403.00272/) (2024)
- [Token Adaptation via Side Graph Convolution for Efficient Fine-tuning of 3D Point Cloud Transformers](https://mlsanity.com/paper/2502.14142/) (2025)
- [Group-disentangled Representation Learning with Weakly-Supervised Regularization](https://mlsanity.com/paper/2110.12185/) (2021)
- [Isomorphic mesh generation from point clouds with multilayer perceptrons](https://mlsanity.com/paper/2210.14157/) (2022)
- [A Dataset and Framework for Learning State-invariant Object Representations](https://mlsanity.com/paper/2404.06470/) (2024)
- [Beyond Viewpoint: Robust 3D Object Recognition under Arbitrary Views through Joint Multi-Part Representation](https://mlsanity.com/paper/2407.03842/) (2024)
- [Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification](https://mlsanity.com/paper/2505.17666/) (2025)
- [M3CS: Multi-Target Masked Point Modeling with Learnable Codebook and Siamese Decoders](https://mlsanity.com/paper/2309.13235/) (2023)
- [Deeply Dual Supervised learning for melanoma recognition](https://mlsanity.com/paper/2508.01994/) (2025)
- [Edge Detection for Organ Boundaries via Top Down Refinement and SubPixel Upsampling](https://mlsanity.com/paper/2508.06805/) (2025)
- [DualResolution Residual Architecture with Artifact Suppression for Melanocytic Lesion Segmentation](https://mlsanity.com/paper/2508.06816/) (2025)
- [VesselRW: Weakly Supervised Subcutaneous Vessel Segmentation via Learned Random Walk Propagation](https://mlsanity.com/paper/2508.06819/) (2025)

## Abstract (arXiv)

Fine-grained 3D shape classification is important for shape understanding and analysis, which poses a challenging research problem. However, the studies on the fine-grained 3D shape classification have rarely been explored, due to the lack of fine-grained 3D shape benchmarks. To address this issue, we first introduce a new 3D shape dataset (named FG3D dataset) with fine-grained class labels, which consists of three categories including airplane, car and chair. Each category consists of several subcategories at a fine-grained level. According to our experiments under this fine-grained dataset, we find that state-of-the-art methods are significantly limited by the small variance among subcategories in the same category. To resolve this problem, we further propose a novel fine-grained 3D shape classification method named FG3D-Net to capture the fine-grained local details of 3D shapes from multiple rendered views. Specifically, we first train a Region Proposal Network (RPN) to detect the generally semantic parts inside multiple views under the benchmark of generally semantic part detection. Then, we design a hierarchical part-view attention aggregation module to learn a global shape representation by aggregating generally semantic part features, which preserves the local details of 3D shapes. The part-view attention module hierarchically leverages part-level and view-level attention to increase the discriminability of our features. The part-level attention highlights the important parts in each view while the view-level attention highlights the discriminative views among all the views of the same object. In addition, we integrate a Recurrent Neural Network (RNN) to capture the spatial relationships among sequential views from different viewpoints. Our results under the fine-grained 3D shape dataset show that our method outperforms other state-of-the-art methods.