VoxelDiffusionCut: Non-destructive Internal-part Extraction via Iterative Cutting and Structure Estimation

2026-02-21

AI Summary

This study addresses the challenge of non-destructively extracting target internal components—such as batteries or motors—from complex products when disassembly information is unavailable. The authors propose a strategy based on iterative cutting and structural estimation: after each cut, a conditional diffusion model voxelizes the newly exposed cross-section to reconstruct the probabilistic distribution of the internal structure, which in turn informs the planning of safe subsequent cutting paths. This work presents the first application of diffusion models to conditional voxel-based reconstruction, effectively capturing multimodal uncertainties and avoiding the overconfident predictions typical of traditional methods suffering from mode collapse. Simulation experiments demonstrate that the approach accurately estimates internal geometry and leverages uncertainty to guide decision-making, successfully enabling non-destructive extraction of target components.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: State Estimation
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Non-destructive extraction of the target internal part, such as batteries and motors, by cutting surrounding structures is crucial at recycling and disposal sites. However, the diversity of products and the lack of information on disassembly procedures make it challenging to decide where to cut. This study explores a method for non-destructive extraction of a target internal part that iteratively estimates the internal structure from observed cutting surfaces and formulates cutting plans based on the estimation results. A key requirement is to estimate the probability of the target part's presence from partial observations. However, learning conditional generative models for this task is challenging: The high dimensionality of 3D shape representations makes learning difficult, and conventional models (e.g., conditional variational autoencoders) often fail to capture multi-modal predictive uncertainty due to mode collapse, resulting in overconfident predictions. To address these issues, we propose VoxelDiffusionCut, which iteratively estimates the internal structure represented as voxels using a diffusion model and plans cuts for non-destructive extraction of the target internal part based on the estimation results. Voxel representation allows the model to predict only attributes at fixed grid positions, i.e., types of constituent parts, making learning more tractable. The diffusion model completes the voxel representation conditioned on observed cutting surfaces, capturing uncertainty in unobserved regions to avoid erroneous cuts. Experimental results in simulation suggest that the proposed method can estimate internal structures from observed cutting surfaces and enable non-destructive extraction of the target internal part by leveraging the estimated uncertainty.

Problem

• non-destructive extraction
• internal-part extraction
• structure estimation
• cutting planning
• 3D shape uncertainty

Innovation

• VoxelDiffusionCut
• diffusion model
• non-destructive extraction
• iterative cutting
• uncertainty-aware structure estimation