# Angular Triplet-Center Loss for Multi-view 3D Shape Retrieval

arXiv: https://arxiv.org/abs/1811.08622 · HTML: https://mlsanity.com/paper/1811.08622/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2018.

## Built on by (most cited first, 11 of 11)

- [Zero-Shot Learning on 3D Point Cloud Objects and Beyond](https://mlsanity.com/paper/2104.04980/) (2021)
- [Fine-Grained VR Sketching: Dataset and Insights](https://mlsanity.com/paper/2209.10008/) (2022)
- [Describe, Adapt and Combine: Empowering CLIP Encoders for Open-set 3D Object Retrieval](https://mlsanity.com/paper/2507.21489/) (2025)
- [Towards 3D VR-Sketch to 3D Shape Retrieval](https://mlsanity.com/paper/2209.10020/) (2022)
- [Center-Based Relaxed Learning Against Membership Inference Attacks](https://mlsanity.com/paper/2404.17674/) (2024)
- [A Survey of Historical Learning: Learning Models with Learning History](https://mlsanity.com/paper/2303.12992/) (2023)
- [SCA-PVNet: Self-and-Cross Attention Based Aggregation of Point Cloud and Multi-View for 3D Object Retrieval](https://mlsanity.com/paper/2307.10601/) (2023)
- [PEVA-Net: Prompt-Enhanced View Aggregation Network for Zero/Few-Shot Multi-View 3D Shape Recognition](https://mlsanity.com/paper/2404.19168/) (2024)
- [VSFormer: Mining Correlations in Flexible View Set for Multi-view 3D Shape Understanding](https://mlsanity.com/paper/2409.09254/) (2024)
- [Tragedy Plus Time: Capturing Unintended Human Activities from Weakly-labeled Videos](https://mlsanity.com/paper/2204.13548/) (2022)
- [DINO Eats CLIP: Adapting Beyond Knowns for Open-set 3D Object Retrieval](https://mlsanity.com/paper/2604.19432/) (2026)

## Abstract (arXiv)

How to obtain the desirable representation of a 3D shape, which is discriminative across categories and polymerized within classes, is a significant challenge in 3D shape retrieval. Most existing 3D shape retrieval methods focus on capturing strong discriminative shape representation with softmax loss for the classification task, while the shape feature learning with metric loss is neglected for 3D shape retrieval. In this paper, we address this problem based on the intuition that the cosine distance of shape embeddings should be close enough within the same class and far away across categories. Since most of 3D shape retrieval tasks use cosine distance of shape features for measuring shape similarity, we propose a novel metric loss named angular triplet-center loss, which directly optimizes the cosine distances between the features. It inherits the triplet-center loss property to achieve larger inter-class distance and smaller intra-class distance simultaneously. Unlike previous metric loss utilized in 3D shape retrieval methods, where Euclidean distance is adopted and the margin design is difficult, the proposed method is more convenient to train feature embeddings and more suitable for 3D shape retrieval. Moreover, the angle margin is adopted to replace the cosine margin in order to provide more explicit discriminative constraints on an embedding space. Extensive experimental results on two popular 3D object retrieval benchmarks, ModelNet40 and ShapeNetCore 55, demonstrate the effectiveness of our proposed loss, and our method has achieved state-of-the-art results on various 3D shape datasets.