SOURCE-LINKED INTELLIGENCE

Attention-DP3: Spatially Object-aware 3D Diffusion Policy via Geometry-aligned Attentional Conditioning

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

3D point-cloud observations are inherently ambiguous in complex, cluttered manipulation scenes, where target objects may be partially occluded or tightly intermingled with visually similar distractors. As a result, standard 3D diffusion policies often struggle to localize and exploit task-relevant geometry as scene complexity grows. We propose \textbf{Attention-DP3}, a spatially object-aware 3D diffusion policy that injects object-level geometric cues via attention while keeping the DP3 diffusion backbone unchanged. Our pipeline performs open-vocabulary 2D segmentation on RGB images, then lift

Read original source ↗ Open in workspace

recordType

paper

region

Global