F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation

This paper studies category-level RGB-D object pose estimation, which recovers an object's 3D rotation and translation without instance-specific CAD models or reference views. This task is highly ambiguous due to intra-class variations, symmetries, and partial observations. Current solutions struggle to balance reliability and efficiency: methods based on intermediate structures are prone to error propagation, while diffusion models suffer from high inference latency and complex post-hoc candidate extraction. To address this, we present F2G-Pose, a real-time direct, single-pass framework that predicts category-level pose, metric size, and camera-frame completed shape from a single RGB-D observation in one feed-forward pass. F2G-Pose lifts dense visual foundation features to partial point clouds, encodes local geometry with DGCNN tokenization, and integrates object-level structure with a Mixture-of-Experts Transformer. Joint size prediction and camera-frame shape completion encourage metric consistency through dense geometric supervision. With its task-specific network trained only on pose-annotated synthetic SOPE data and its frozen RADIO backbone externally pretrained, F2G-Pose achieves state-of-the-art accuracy on SOPE and ROPE while running at 28 FPS for pose-only inference, and further demonstrates strong camera-frame geometry on HouseCat6D and real-object transfer on HANDAL. Analyses of latency, robustness, shape completion, and GenPose++ candidate behavior further demonstrate the efficiency and reliability of F2G-Pose, with real-world manipulation experiments demonstrating deployment potential under segmented RGB-D inputs. The project page, code, and pretrained models are made available at https://jrryzh.github.io/F2G-Pose/.

Jinyu Zhang, Haitao Lin, Jiashu Hou, Xiangyang Xue, Yanwei Fu

Leverage3 / 5

A method or resource many groups across the field will adopt within a year.

24% of this desk’s rubric

Magnitude3 / 5

Large gain: roughly 2x, or a clear new state of the art on a hard, unsaturated problem.

18% of this desk’s rubric

Evidence3 / 5

Solid: multiple benchmarks or cohorts, ablations, fair baselines, released code or data.

14% of this desk’s rubric

Novelty3 / 5

A genuinely new approach to an open problem.

16% of this desk’s rubric

Trajectory2 / 5

Some room to improve with obvious engineering.

18% of this desk’s rubric

Stakes2 / 5

Benefits a professional community (practitioners, clinicians, engineers).

10% of this desk’s rubric

• Hugging Face upvotes5 (reference 25, via hf-daily, Oct 24, 2026, 02:05 UTC)
• GitHub stars24 (reference 250, via hf-daily, Oct 24, 2026, 02:05 UTC)

• Reviewed by heuristic-v7 on Oct 23, 2026, 02:53 UTC. Paper type: method.
• Categories: cs.CV
• BRIEF, No.10 in the Artificial Intelligence edition of October 24, 2026.