Box6D : Zero-shot Category-level 6D Pose Estimation of Warehouse Boxes

2025-11-19

AI Summary

This paper addresses the challenging problem of 6D pose estimation for box-like objects under cluttered and occluded conditions in warehouse scenarios. We propose a zero-shot category-level method that requires no instance-level CAD models. Our approach jointly estimates both 6D pose and object dimensions by integrating category-level CAD templates with binary search, augmented by depth-based confidence filtering and an early-stopping mechanism. Taking RGB-D input, the method leverages depth maps for hypothesis generation, pruning, and refinement—ensuring high accuracy while substantially improving inference efficiency. Evaluated on a real-world warehouse dataset and public benchmarks, our method achieves state-of-the-art pose accuracy and accelerates inference by 76% over prior work. It demonstrates strong generalization across unseen instances and practical applicability in industrial settings.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Object Detection & Categorization
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Accurate and efficient 6D pose estimation of novel objects under clutter and occlusion is critical for robotic manipulation across warehouse automation, bin picking, logistics, and e-commerce fulfillment. There are three main approaches in this domain; Model-based methods assume an exact CAD model at inference but require high-resolution meshes and transfer poorly to new environments; Model-free methods that rely on a few reference images or videos are more flexible, however often fail under challenging conditions; Category-level approaches aim to balance flexibility and accuracy but many are overly general and ignore environment and object priors, limiting their practicality in industrial settings. To this end, we propose Box6d, a category-level 6D pose estimation method tailored for storage boxes in the warehouse context. From a single RGB-D observation, Box6D infers the dimensions of the boxes via a fast binary search and estimates poses using a category CAD template rather than instance-specific models. Suing a depth-based plausibility filter and early-stopping strategy, Box6D then rejects implausible hypotheses, lowering computational cost. We conduct evaluations on real-world storage scenarios and public benchmarks, and show that our approach delivers competitive or superior 6D pose precision while reducing inference time by approximately 76%.

Problem

• Estimating 6D poses of warehouse boxes under clutter and occlusion
• Balancing flexibility and accuracy for novel object pose estimation
• Reducing computational cost while maintaining competitive pose precision

Innovation

• Uses binary search for box dimension inference
• Employs category CAD template for pose estimation
• Applies depth filter for hypothesis plausibility check