# Fudan's F2G-Pose predicts 6D pose, metric size and full shape from one RGB-D frame at 28 frames per second

The NeurIPS 2026 method lifts foundation-model features onto point clouds and routes them through an eight-expert transformer, running about seven times faster than diffusion-based GenPose++.

- Conviction: 40 / 100 (forming)
- Horizon: Emerging (watchlist)
- Tracking since: 2026-10-24T00:00:00.000Z
- Last updated: 2026-10-24T06:43:21.582Z
- Canonical: https://polylog.news/ai/trends/event-fudan-s-f2g-pose-predicts-6d-pose-metric-size-and-full-shape
- Publisher: Polylog
- Affected regions: China

## Recent evidence

- [neutral] Fudan's F2G-Pose predicts 6D pose, metric size and full shape from one RGB-D frame at 28 frames per second (2026-10-24): Auto-opened to track an article no existing trend covered.