3D-CBM: A Framework for Concept-Based Interpretability in Generative 3D Modeling
Quick Answer
This paper shows that The 3D-CBM framework integrates Concept Bottleneck Models into 3D generative architectures, achieving 88.8% concept prediction accuracy and enabling interactive error correction in safety-critical applications.
Quick Take
The 3D-CBM framework integrates Concept Bottleneck Models into 3D generative architectures, achieving 88.8% concept prediction accuracy and enabling interactive error correction in safety-critical applications. This approach addresses the semantic gap in deep geometric learning, paving the way for semantically-steerable 3D generation.
Key Points
- 3D-CBM maps raw geometric inputs into interpretable primitives and attributes.
- Utilizes datasets like PartNet and ShapeNet for concept-based supervision.
- Achieved a Chamfer Distance of 0.0115 in experiments.
- Enables precise test-time intervention for structural error correction.
- Establishes a foundation for collaborative human-in-the-loop design systems.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 11446v1 Announce Type: new Abstract: This research introduces a framework for incorporating Concept Bottleneck Models (CBMs) into 3D generative architectures to address the inherent 'semantic gap' in deep geometric learning. As deep models become central to 3D content creation, explainability shifts from a peripheral feature to a fundamental requirement for trust and accountability in safety-critical domains such as healthcare and manufacturing.
CBMs provide an intrinsic interpretability solution by constraining latent representations to align with human-defined concepts, yet their application to unstructured 3D data remains largely unexplored. We design, implement, and validate a formal 3D-CBM architecture that maps raw geometric inputs, including point clouds and meshes, into a multi-tiered taxonomy of interpretable primitives and functional attributes.
The framework further identifies strategic datasets, such as PartNet and ShapeNet, specialized for concept-based supervision. Experimental results from a 3D part-manipulation proof-of-concept experiment demonstrate the framework's efficacy, achieving a concept prediction accuracy of 88. 8\% and a Chamfer Distance of 0. 0115. Critically, the model enables precise test-time intervention, allowing for the interactive correction of structural errors.
This work establishes a foundation for semantically-steerable 3D generation and invites further exploration into collaborative human-in-the-loop design systems.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.