Single-View Shape Completion for Robotic Grasping in Clutter

2025-12-18

AI Summary

To address degraded grasping performance caused by geometric incompleteness in single-view depth observations of cluttered scenes, this paper proposes the first category-level, single-view 3D shape completion and grasping co-optimization framework tailored for real-world home environments. Methodologically, it integrates diffusion-model-driven 3D shape generation, category-prior-guided implicit surface reconstruction, and single-frame depth encoding with cross-modal geometric completion—thereby relaxing the conventional isolated-object assumption. Evaluated on real cluttered scenes, our approach achieves a 23% higher grasp success rate over a no-completion baseline and a 19% improvement over state-of-the-art shape completion methods. The framework establishes a generalizable, geometry-aware foundation for vision–action coordination. Code is publicly released.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: Manipulation
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

In vision-based robot manipulation, a single camera view can only capture one side of objects of interest, with additional occlusions in cluttered scenes further restricting visibility. As a result, the observed geometry is incomplete, and grasp estimation algorithms perform suboptimally. To address this limitation, we leverage diffusion models to perform category-level 3D shape completion from partial depth observations obtained from a single view, reconstructing complete object geometries to provide richer context for grasp planning. Our method focuses on common household items with diverse geometries, generating full 3D shapes that serve as input to downstream grasp inference networks. Unlike prior work, which primarily considers isolated objects or minimal clutter, we evaluate shape completion and grasping in realistic clutter scenarios with household objects. In preliminary evaluations on a cluttered scene, our approach consistently results in better grasp success rates than a naive baseline without shape completion by 23% and over a recent state of the art shape completion approach by 19%. Our code is available at https://amm.aass.oru.se/shape-completion-grasping/.

Problem

• Complete 3D shapes from single-view depth for grasp planning
• Improve robotic grasping in cluttered scenes with occluded objects
• Use diffusion models to reconstruct geometry for household items

Innovation

• Uses diffusion models for 3D shape completion
• Generates full shapes from single-view depth observations
• Focuses on cluttered household object scenarios