Newest papers

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

Jinyu Zhang, Haitao Lin, Jiashu Hou, Xiangyang Xue, Yanwei Fu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31623 · cited by 0 works (OpenAlex) · open-access PDF

Japanese

このペーパーは、カテゴリレベルのRGB-Dオブジェクトポーズ評価を実行可能なカテゴリレベルの変動、シンメトリー、および部分的な観測のために非常に曖昧である。現在のソリューションは、中間構造に基づく3D回転と翻訳を回復し、インスタンス特有のCADモデルや参照ビューなしでリリースします。このタスクは、クラス内変動、シンメトリー、および部分的な観測のために非常に曖昧です。現在のソリューションは、信頼性と効率のバランスを予測するために苦労しています:中間構造に基づく方法は、単一のRGB-D観測からエラーを起こす可能性があります。 F2G-Poseコード

Machine translation (Meta M2M100); the English original follows.

Abstract

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/.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Artificial intelligence, Pose, Computer vision, Consistency (knowledge bases), Rotation (mathematics)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange