PiCo: Active Manifold Canonicalization for Robust Robotic Visual Anomaly Detection

TL;DR

PiCo introduces an active approach to robotic visual anomaly detection that projects observations onto a condition-invariant manifold, significantly improving robustness under diverse and unstable operating conditions.

Contribution

The paper proposes PiCo, a unified framework for active manifold canonicalization combining physical reorientation and neural denoising to enhance anomaly detection in robotics.

Findings

Achieves 93.7% O-AUROC on M2AD benchmark, outperforming prior methods.

Attains 98.5% accuracy in active closed-loop scenarios.

Demonstrates robustness under diverse pose and illumination conditions.

Abstract

Industrial deployment of robotic visual anomaly detection (VAD) is fundamentally constrained by passive perception under diverse 6-DoF pose configurations and unstable operating conditions such as illumination changes and shadows, where intrinsic semantic anomalies and physical disturbances coexist and interact. To overcome these limitations, a paradigm shift from passive feature learning to Active Canonicalization is proposed. PiCo (Pose-in-Condition Canonicalization) is introduced as a unified framework that actively projects observations onto a condition-invariant canonical manifold. PiCo operates through a cascaded mechanism. The first stage, Active Physical Canonicalization, enables a robotic agent to reorient objects in order to reduce geometric uncertainty at its source. The second stage, Neural Latent Canonicalization, adopts a three-stage denoising hierarchy consisting of photometric processing at the input level, latent refinement at the feature level, and contextual reasoning at the semantic level, progressively eliminating nuisance factors across representational scales. Extensive evaluations on the large-scale M2AD benchmark demonstrate the superiority of this paradigm. PiCo achieves a state-of-the-art 93.7% O-AUROC, representing a 3.7% improvement over prior methods in static settings, and attains 98.5% accuracy in active closed-loop scenarios. These results demonstrate that active manifold canonicalization is critical for robust embodied perception.