Fudan's F2G-Pose Estimates 6D Pose and Shape from a Single RGB-D Image

Fudan University and Shanghai researchers introduced F2G-Pose, a real-time feed-forward framework that jointly estimates category-level 6D pose, metric size, and completed shape from a single segmented RGB-D image, using dense visual features from RADIO v2.5 fused with point clouds.

2026-10-23 ~ 2026-10-24 · 2 related posts

• F2G-Pose: real-time category-level pose estimation from a single RGB-D image — sii-research · 2026-10-23
• Fudan's F2G-Pose estimates 6D pose, size and shape from one RGB-D image at 28 FPS — joemeno · 2026-10-24