LLM-supported 3D Modeling Tool for Radio Radiance Field Reconstruction

2026-03-04

AI Summary

This work proposes the first chat-based local tool that integrates a fine-tuned language model with generative 3D modeling to facilitate radio radiation field (RRF) reconstruction. Traditional RRF reconstruction relies on high-fidelity 3D environment models requiring specialized measurements and computer vision expertise, resulting in high barriers to entry and limited accessibility. In contrast, the proposed system enables users to rapidly construct scene models suitable for RRF reconstruction through natural language instructions. It leverages a fine-tuned T5-mini model for instruction parsing, semantic retrieval via all-MiniLM-L6-v2, and 3D mesh generation using LLaMA-Mesh and Shap-E, all integrated into an RF-3DGS pipeline through a custom Blender plugin. Experiments in the NIST atrium and UW-Madison wireless lab demonstrate that this approach substantially reduces modeling complexity and enhances the practicality and accessibility of RRF techniques.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: 3D Computer Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Large language models for search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurate channel estimation is essential for massive multiple-input multiple-output (MIMO) technologies in next-generation wireless communications. Recently, the radio radiance field (RRF) has emerged as a promising approach for wireless channel modeling, offering a comprehensive spatial representation of channels based on environmental geometry. State-of-the-art RRF reconstruction methods, such as RF-3DGS, can render channel parameters, including gain, angle of arrival, angle of departure, and delay, within milliseconds. However, creating the required 3D environment typically demands precise measurements and advanced computer vision techniques, limiting accessibility. This paper introduces a locally deployable tool that simplifies 3D environment creation for RRF reconstruction. The system combines finetuned language models, generative 3D modeling frameworks, and Blender integration to enable intuitive, chat-based scene design. Specifically, T5-mini is finetuned for parsing user commands, while all-MiniLM-L6-v2 supports semantic retrieval from a local object library. For model generation, LLaMA-Mesh provides fast mesh creation, and Shap-E delivers high-quality outputs. A custom Blender export plugin ensures compatibility with the RF-3DGS pipeline. We demonstrate the tool by constructing 3D models of the NIST lobby and the UW-Madison wireless lab, followed by corresponding RRF reconstructions. This approach significantly reduces modeling complexity, enhancing the usability of RRF for wireless research and spectrum planning.

Problem

• radio radiance field
• 3D modeling
• channel estimation
• massive MIMO
• wireless channel modeling

Innovation

• LLM-supported 3D modeling
• radio radiance field
• generative 3D reconstruction
• chat-based scene design
• RF-3DGS integration