CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligence

2025-12-14

AI Summary

To address low reliability, poor interpretability, and weak cross-modal alignment in 3D understanding and generation—stemming from the absence of explicit reasoning mechanisms—this paper proposes the first collaborative reasoning framework for 3D intelligence. Methodologically, it introduces spatially anchored latent-space decomposition, jointly enabling semantic chain-of-thought reasoning (Spatial-CoT) and structured spatial reasoning to achieve end-to-end controllable modeling from language intent to geometric generation; it further incorporates geometry-aware latent decomposition and cross-modal alignment constraints. The core contribution is the first unified modeling of semantic and spatial reasoning, supporting compositional and procedural 3D geometric reasoning. Evaluated on ShapeNet and Objaverse, our method achieves a +12.6% improvement in CLIP-3D score and a 9.3% reduction in Chamfer distance, significantly outperforming state-of-the-art approaches.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Computer Vision: 3D Computer Vision
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Recent advances in large multimodal models suggest that explicit reasoning mechanisms play a critical role in improving model reliability, interpretability, and cross-modal alignment. While such reasoning-centric approaches have been proven effective in language and vision tasks, their extension to 3D remains underdeveloped. CoRe3D introduces a unified 3D understanding and generation reasoning framework that jointly operates over semantic and spatial abstractions, enabling high-level intent inferred from language to directly guide low-level 3D content formation. Central to this design is a spatially grounded reasoning representation that decomposes 3D latent space into localized regions, allowing the model to reason over geometry in a compositional and procedural manner. 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.

Problem

• Extends reasoning-centric approaches to 3D understanding and generation
• Decomposes 3D latent space for compositional and procedural reasoning
• Aligns semantic inference with spatial reasoning for consistent 3D outputs

Innovation

• Unified 3D reasoning framework for understanding and generation
• Spatially grounded representation decomposing 3D latent space
• Coupling semantic chain-of-thought with structured spatial reasoning