OneViewAll: Semantic Prior Guided One-View 6D Pose Estimation for Novel Objects

TL;DR

OneViewAll is a novel semantic-prior-guided framework for single-view 6D object pose estimation that outperforms existing methods by integrating hierarchical priors and a projection-based alignment approach.

Contribution

It introduces a new Project-and-Compare paradigm and hierarchical semantic priors for scalable, model-free pose estimation from a single RGB-D view.

Findings

Achieves 92.5% ADD-0.1 accuracy on LINEMOD with one reference view.

Significantly outperforms the baseline One2Any (52.6%).

Maintains low inference latency and handles symmetric, occluded objects effectively.

Abstract

In many practical 6D object pose estimation scenarios, we often have access to only a single real-world RGB-D reference view per object, typically without CAD models. Existing methods largely rely on explicit 3D models or multi-view data, which limits their scalability. To address this challenging single-reference model-free setting, we propose \textbf{OneViewAll}, a semantic-prior-guided framework that performs pose estimation via a novel Project-and-Compare paradigm. Instead of relying on computationally expensive CAD-based rendering, our method directly aligns reference and query observations within a projection-equivariant space. OneViewAll progressively integrates hierarchical semantic priors across three levels: (1) \textit{category- and scene-level} priors for efficient hypothesis initialization; (2) \textit{object-level symmetry} priors for geometry completion via mirror fusion; and (3) \textit{patch-level} priors for discriminative refinement. Extensive experiments demonstrate that OneViewAll achieves \textbf{92.5\%} ADD-0.1 accuracy on the LINEMOD dataset using only one real reference view -- significantly outperforming the CVPR 2025 baseline One2Any (52.6\%). It also yields consistent improvements on YCB-V, Real275, and Toyota-Light while maintaining low inference latency. Our results underscore the efficacy of symmetry-aware projection in handling symmetric, texture-less, and occluded objects.