Hard Example Generation By Texture Synthesis For Cross-domain Shape Similarity Learning

Abstract

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

Stats

• citations0
• S2 citations—
• github stars2
• HF likes0
• heat score0.95
• arxiv keyfu2020hard

Related papers

• Optimizing Multi-modal Models For Image-based Shape Retrieval: The Role Of Pre-alignment And Hard Contrastive Learning (2026)0.00
• Zero In On Shape: A Generic 2D-3D Instance Similarity Metric Learned From Synthetic Data (2021)5.84
• Rethinking Loss Design For Large-scale 3D Shape Retrieval (2019)4.52
• 3D Shape Retrieval Via Irrelevance Filtering And Similarity Ranking (IF/SR) (2017)0.00
• Risa-net: Rotation-invariant Structure-aware Network For Fine-grained 3D Shape Retrieval (2020)5.48
• Texture Synthesis Guided Deep Hashing For Texture Image Retrieval (2018)8.35
• Structure-aware 3D VR Sketch To 3D Shape Retrieval (2022)8.94
• Diff-sbsr: Learning Multimodal Feature-enhanced Diffusion Models For Zero-shot Sketch-based 3D Shape Retrieval (2026)0.00