3D-CBM: A Framework for Concept-Based Interpretability in Generative 3D Modeling

• URL: http://arxiv.org/abs/2606.11446v1
• Date: Tue, 09 Jun 2026 20:57:03 GMT
• Title: 3D-CBM: A Framework for Concept-Based Interpretability in Generative 3D Modeling
• Abstract summary: This research introduces a framework for incorporating Concept Bottleneck Models (CBMs) into 3D generative architectures.<n>CBMs provide an intrinsic interpretability solution by constraining latent representations to align with human-defined concepts.<n>We design, implement, and validate a formal 3D-CBM architecture that maps raw geometric inputs, including point clouds and meshes, into a taxonomy of interpretable primitives and functional attributes.
• Score: 0.7614628596146601
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• A Persistent Homology Design Space for 3D Point Cloud Deep Learning [5.810033007426438]
  Persistent Homology (PH) offers stable, multi-scale descriptors of intrinsic shape structure.<n>Despite strong theoretical guarantees and increasing empirical adoption, its integration into deep learning for point clouds remains largely ad hoc and architecturally peripheral.<n>In this work, we introduce a unified design space for Persistent-Homology driven learning in 3D point clouds.
  arXiv  Detail & Related papers  (2026-04-05T22:38:37Z)
• World2Mind: Cognition Toolkit for Allocentric Spatial Reasoning in Foundation Models [25.135316296678187]
  Existing methods either overfit statistical shortcuts via 3D grounding data or remain confined to 2D visual perception.<n>We propose World2Mind, a training-free spatial intelligence toolkit.<n>We show that World2Mind boosts the performance of frontier models, such as GPT-5.2, by 5%18%.
  arXiv  Detail & Related papers  (2026-03-10T15:12:14Z)
• TFusionOcc: Student's t-Distribution Based Object-Centric Multi-Sensor Fusion Framework for 3D Occupancy Prediction [8.44168738898516]
  This paper introduces TFusionOcc, a novel object-centric multi-sensor fusion framework for predicting 3D semantic occupancy.<n>By leveraging multi-stage multi-sensor fusion, Student's t-distribution, and the T-Mixture model (TMM), the proposed method achieved state-of-the-art (SOTA) performance on the nuScenes benchmark.
  arXiv  Detail & Related papers  (2026-02-06T05:43:42Z)
• Lemon: A Unified and Scalable 3D Multimodal Model for Universal Spatial Understanding [80.66591664266744]
  Lemon is a unified transformer architecture that processes 3D point cloud patches and language tokens as a single sequence.<n>To handle the complexity of 3D data, we develop a structured patchification and tokenization scheme that preserves spatial context.<n>Lemon establishes new state-of-the-art performance across comprehensive 3D understanding and reasoning tasks.
  arXiv  Detail & Related papers  (2025-12-14T20:02:43Z)
• CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligence [6.2150701899678635]
  CoRe3D introduces a unified 3D understanding and generation reasoning framework that jointly operates over semantic and spatial abstractions.<n>By tightly coupling semantic chain-of-thought inference with structured spatial reasoning, CoRe3D produces 3D outputs that exhibit strong local consistency and faithful alignment with linguistic descriptions.
  arXiv  Detail & Related papers  (2025-12-14T17:05:11Z)
• OPFormer: Object Pose Estimation leveraging foundation model with geometric encoding [2.1987601456703474]
  We introduce a unified, end-to-end framework that seamlessly integrates object detection and pose estimation.<n>Our system first employs the CNOS detector to localize target objects.<n>For each detection, our novel pose estimation module, OPFormer, infers the precise 6D pose.
  arXiv  Detail & Related papers  (2025-11-16T14:19:52Z)
• MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts [50.37005070020306]
  MoRE is a dense 3D visual foundation model based on a Mixture-of-Experts (MoE) architecture.<n>MoRE incorporates a confidence-based depth refinement module that stabilizes and refines geometric estimation.<n>It integrates dense semantic features with globally aligned 3D backbone representations for high-fidelity surface normal prediction.
  arXiv  Detail & Related papers  (2025-10-31T06:54:27Z)
• Spatial Understanding from Videos: Structured Prompts Meet Simulation Data [89.77871049500546]
  We present a unified framework for enhancing 3D spatial reasoning in pre-trained vision-language models without modifying their architecture.<n>This framework combines SpatialMind, a structured prompting strategy that decomposes complex scenes and questions into interpretable reasoning steps, with ScanForgeQA, a scalable question-answering dataset built from diverse 3D simulation scenes.
  arXiv  Detail & Related papers  (2025-06-04T07:36:33Z)
• Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding [58.38294408121273]
  We propose Cross-modal and Uncertainty-aware Agglomeration for Open-vocabulary 3D Scene Understanding dubbed CUA-O3D.<n>Our method addresses two key challenges: (1) incorporating semantic priors from VLMs alongside the geometric knowledge of spatially-aware vision foundation models, and (2) using a novel deterministic uncertainty estimation to capture model-specific uncertainties.
  arXiv  Detail & Related papers  (2025-03-20T20:58:48Z)
• JADE: Joint-aware Latent Diffusion for 3D Human Generative Modeling [62.77347895550087]
  We introduce JADE, a generative framework that learns the variations of human shapes with fined-grained control.<n>Our key insight is a joint-aware latent representation that decomposes human bodies into skeleton structures.<n>To generate coherent and plausible human shapes under our proposed decomposition, we also present a cascaded pipeline.
  arXiv  Detail & Related papers  (2024-12-29T14:18:35Z)
• Geometric Deep Learning for Structure-Based Drug Design: A Survey [83.87489798671155]
  Structure-based drug design (SBDD) leverages the three-dimensional geometry of proteins to identify potential drug candidates. Recent advancements in geometric deep learning, which effectively integrate and process 3D geometric data, have significantly propelled the field forward.
  arXiv  Detail & Related papers  (2023-06-20T14:21:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.