# Hard Example Generation by Texture Synthesis for Cross-domain Shape Similarity Learning

arXiv: https://arxiv.org/abs/2010.12238 · HTML: https://mlsanity.com/paper/2010.12238/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2020.

## Built on by (most cited first, 8 of 8)

- [Generalizing Single-View 3D Shape Retrieval to Occlusions and Unseen Objects](https://mlsanity.com/paper/2401.00405/) (2023)
- [Digital Twin Generation from Visual Data: A Survey](https://mlsanity.com/paper/2504.13159/) (2025)
- [COM3D: Leveraging Cross-View Correspondence and Cross-Modal Mining for 3D Retrieval](https://mlsanity.com/paper/2405.04103/) (2024)
- [MXM-CLR: A Unified Framework for Contrastive Learning of Multifold Cross-Modal Representations](https://mlsanity.com/paper/2303.10839/) (2023)
- [Shape and Texture Recognition in Large Vision-Language Models](https://mlsanity.com/paper/2503.23062/) (2025)
- [PReP: Efficient context-based shape retrieval for missing parts](https://mlsanity.com/paper/2410.14245/) (2024)
- [Optimizing Multi-Modal Models for Image-Based Shape Retrieval: The Role of Pre-Alignment and Hard Contrastive Learning](https://mlsanity.com/paper/2603.06982/) (2026)
- [PASR: Pose-Aware 3D Shape Retrieval from Occluded Single Views](https://mlsanity.com/paper/2604.22658/) (2026)

## Abstract (arXiv)

Image-based 3D shape retrieval (IBSR) aims to find the corresponding 3D shape of a given 2D image from a large 3D shape database. The common routine is to map 2D images and 3D shapes into an embedding space and define (or learn) a shape similarity measure. While metric learning with some adaptation techniques seems to be a natural solution to shape similarity learning, the performance is often unsatisfactory for fine-grained shape retrieval. In the paper, we identify the source of the poor performance and propose a practical solution to this problem. We find that the shape difference between a negative pair is entangled with the texture gap, making metric learning ineffective in pushing away negative pairs. To tackle this issue, we develop a geometry-focused multi-view metric learning framework empowered by texture synthesis. The synthesis of textures for 3D shape models creates hard triplets, which suppress the adverse effects of rich texture in 2D images, thereby push the network to focus more on discovering geometric characteristics. Our approach shows state-of-the-art performance on a recently released large-scale 3D-FUTURE[1] repository, as well as three widely studied benchmarks, including Pix3D[2], Stanford Cars[3], and Comp Cars[4]. Codes will be made publicly available at: https://github.com/3D-FRONT-FUTURE/IBSR-texture