Beyond Viewpoint: Robust 3D Object Recognition under Arbitrary Views through Joint Multi-Part Representation

TL;DR

This paper introduces PANet, a part-aware network that localizes and understands 3D object parts to achieve robust recognition from arbitrary, unaligned viewpoints, outperforming existing methods on benchmark datasets.

Contribution

The paper proposes a novel part-based representation method, PANet, that enhances 3D object recognition under arbitrary views by leveraging viewpoint invariance and rotation robustness.

Findings

Outperforms existing view-based aggregation methods on benchmark datasets.

Achieves higher accuracy in recognizing objects from arbitrary, unaligned viewpoints.

Surpasses most fixed viewpoint methods in 3D object recognition tasks.

Abstract

Existing view-based methods excel at recognizing 3D objects from predefined viewpoints, but their exploration of recognition under arbitrary views is limited. This is a challenging and realistic setting because each object has different viewpoint positions and quantities, and their poses are not aligned. However, most view-based methods, which aggregate multiple view features to obtain a global feature representation, hard to address 3D object recognition under arbitrary views. Due to the unaligned inputs from arbitrary views, it is challenging to robustly aggregate features, leading to performance degradation. In this paper, we introduce a novel Part-aware Network (PANet), which is a part-based representation, to address these issues. This part-based representation aims to localize and understand different parts of 3D objects, such as airplane wings and tails. It has properties such as viewpoint invariance and rotation robustness, which give it an advantage in addressing the 3D object recognition problem under arbitrary views. Our results on benchmark datasets clearly demonstrate that our proposed method outperforms existing view-based aggregation baselines for the task of 3D object recognition under arbitrary views, even surpassing most fixed viewpoint methods.