Open-Pose 3D zero-shot learning: Benchmark and challenges

Zhao, Weiguang; Yang, Guanyu; Zhang, Rui; Jiang, Chenru; Yang, Chaolong; Yan, Yuyao; Hussain, Amir; Huang, Kaizhu

Abstract

With the explosive 3D data growth, the urgency of utilizing zero-shot learning to facilitate data labeling becomes evident. Recently, methods transferring language or language-image pre-training models like Contrastive Language-Image Pre-training (CLIP) to 3D vision have made significant progress in the 3D zero-shot classification task. These methods primarily focus on 3D object classification with an aligned pose; such a setting is, however, rather restrictive, which overlooks the recognition of 3D objects with open poses typically encountered in real-world scenarios, such as an overturned chair or a lying teddy bear. To this end, we propose a more realistic and challenging scenario named open-pose 3D zero-shot classification, focusing on the recognition of 3D objects regardless of their orientation. First, we revisit the current research on 3D zero-shot classification and propose two benchmark datasets specifically designed for the open-pose setting. We empirically validate many of the most popular methods in the proposed open-pose benchmark. Our investigations reveal that most current 3D zero-shot classification models suffer from poor performance, indicating a substantial exploration room towards the new direction. Furthermore, we study a concise pipeline with an iterative angle refinement mechanism that automatically optimizes one ideal angle to classify these open-pose 3D objects. In particular, to make validation more compelling and not just limited to existing CLIP-based methods, we also pioneer the exploration of knowledge transfer based on Diffusion models. While the proposed solutions can serve as a new benchmark for open-pose 3D zero-shot classification, we discuss the complexities and challenges of this scenario that remain for further research development. The code is available publicly at https://github.com/weiguangzhao/Diff-OP3D

Citation

Zhao, W., Yang, G., Zhang, R., Jiang, C., Yang, C., Yan, Y., Hussain, A., & Huang, K. (2025). Open-Pose 3D zero-shot learning: Benchmark and challenges. Neural Networks, 181, Article 106775. https://doi.org/10.1016/j.neunet.2024.106775

• Journal Article Type: Article
• Acceptance Date: Sep 29, 2024
• Online Publication Date: Oct 9, 2024
• Publication Date: 2025-01
• Deposit Date: Nov 6, 2024
• Journal: Neural Networks
• Print ISSN: 0893-6080
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 181
• Article Number: 106775
• DOI: https://doi.org/10.1016/j.neunet.2024.106775
• Keywords: Zero-shot, 3D classification, Open-pose, Text–image matching