CleanPose: Category-Level Object Pose Estimation via Causal Learning and Knowledge Distillation

TL;DR

CleanPose introduces a causal learning and knowledge distillation framework for category-level object pose estimation, effectively reducing bias from confounders and improving generalization to unseen instances.

Contribution

The paper proposes a novel causal inference module with front-door adjustment and a residual-based knowledge distillation method to enhance pose estimation accuracy and robustness.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Effectively reduces spurious correlations caused by confounders.

Improves generalization to unseen object instances.

Abstract

Category-level object pose estimation aims to recover the rotation, translation and size of unseen instances within predefined categories. In this task, deep neural network-based methods have demonstrated remarkable performance. However, previous studies show they suffer from spurious correlations raised by "unclean" confounders in models, hindering their performance on novel instances with significant variations. To address this issue, we propose CleanPose, a novel approach integrating causal learning and knowledge distillation to enhance category-level pose estimation. To mitigate the negative effect of unobserved confounders, we develop a causal inference module based on front-door adjustment, which promotes unbiased estimation by reducing potential spurious correlations. Additionally, to further improve generalization ability, we devise a residual-based knowledge distillation method that has proven effective in providing comprehensive category information guidance. Extensive experiments across multiple benchmarks (REAL275, CAMERA25 and HouseCat6D) hightlight the superiority of proposed CleanPose over state-of-the-art methods. Code will be available at https://github.com/chrislin0621/CleanPose.