G6D: Geometric Learning-Free RGB-D 6D Pose Solver for Robotic Manipulation

2026-09-20

AI Summary

G6D提出了一种无学习、基于几何的RGB-D 6D姿态求解方法，通过模板匹配和轮廓深度一致性来估计物体姿态，解决了现有方法对计算资源需求高及几何可解释性差的问题。

Abstract

6D object pose estimation is fundamental to robotic manipulation and automation. Recent zero-shot methods have significantly improved generalization to unseen objects, but most still rely on large-scale pretrained models with substantial GPU computation and memory demands. These requirements complicate deployment on robotic platforms where perception, planning, and control share limited computational resources, while learned intermediate representations offer limited geometric interpretability for task-specific adaptation. To address these limitations, we propose G6D, a learning-free, geometry-driven RGB-D 6D pose solver. Given an RGB-D observation, an object instance mask, camera intrinsics, and a CAD model, G6D generates pose hypotheses through template-based geometric matching and refines them using silhouette and depth consistency, forming a purely geometry-driven pose estimation paradigm. This paradigm requires neither pretrained visual models nor target-specific training and preserves interpretable geometric representations throughout pose estimation. Moreover, adjustable hypothesis counts provide flexible accuracy-computation trade-offs, while a CPU-only configuration supports deployment without GPU resources. Experiments on LineMOD and five BOP19 datasets demonstrate advanced performance. Real-world pick-and-place experiments further demonstrate G6D's applicability to robotic manipulation. The complete project is publicly available at https://ai4control.github.io/G6D-Project-Page .

Problem

• 6D Pose Estimation
• Robotic Manipulation
• Zero-shot Methods
• Pretrained Models
• Geometric Interpretability

Innovation

• learning-free
• geometry-driven
• template-based geometric matching
• silhouette and depth consistency
• CPU-only configuration