CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligence
Abstract
A reasoning framework for 3D understanding and generation, CoRe3D, uses spatially grounded reasoning to align high-level language intent with low-level 3D content, ensuring local consistency and alignment with descriptions.
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.
Community
A dual semantic + geometric reasoning framework with octant-based 3D tokens and multi-critic GRPO, achieving SoTA on text-to-3D, image-to-3D, and 3D captioning.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation (2025)
- AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models (2025)
- Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation (2025)
- SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes (2025)
- Let Language Constrain Geometry: Vision-Language Models as Semantic and Spatial Critics for 3D Generation (2025)
- Visual Reasoning Tracer: Object-Level Grounded Reasoning Benchmark (2025)
- Activating Visual Context and Commonsense Reasoning through Masked Prediction in VLMs (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper