Open-Pose 3D Zero-Shot Learning: Benchmark and Challenges
Weiguang Zhao, Guanyu Yang, Rui Zhang, Chenru Jiang, Chaolong Yang, Yuyao Yan, Amir Hussain, Kaizhu Huang
TL;DR
This work reframes 3D zero-shot classification to the open-pose setting, revealing that existing CLIP-based and diffusion-augmented approaches struggle when object orientations are arbitrary. It introduces two open-pose benchmarks by rotating ModelNet40 and McGill data, and proposes a three-component pipeline (Projection, Text-Image Matching, Angle Selection) with Iterative Angle Refinement Mechanism (IARM) to optimize projection angles per class. The authors explore both CLIP-based and diffusion-based text-image matching, demonstrating that diffusion-based knowledge transfer can yield substantial gains in open-pose scenarios, while also highlighting computational trade-offs. Finally, the paper discusses practical challenges and future directions for robust open-pose 3D zero-shot learning, and provides code for reproducibility.
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.