NOCSFlow: Learning Dense Canonical Fields for Monocular Category-Level 9D Pose Estimation

Category-level monocular 9D object pose estimation remains challenging because accurate pose recovery requires reasoning about object geometry from a single RGB observation without explicit geometric information. Dense canonical representations such as Normalized Object Coordinate Space (NOCS) are promising for this problem, as they preserve rich pixel-wise 2D–3D correspondence structure for downstream pose recovery, yet learning such representations directly from monocular RGB remains underexplored. In this work, we introduce NOCSFlow, a pixel-space flow-matching framework that learns dense NOCS representations by injecting features from a pretrained geometry encoder as implicit geometric conditioning into multiple transformer layers. We further introduce coupled supervision that jointly optimizes the generated canonical fields with direct canonical-space supervision and pose-space supervision backpropagated through a differentiable PnP module. Experiments on CAMERA25 and REAL275 demonstrate substantial improvements over prior methods, including $96.8\%$ on the $10^{\circ }$ rotation metric and $85.1\%$ on the joint $(10^{\circ },10\mathrm{cm})$ metric on REAL275.