NeuroVoxel-LM: Language-Aligned 3D Perception via Dynamic Voxelization and Meta-Embedding

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Shiyu, Shan, Lianlei
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916866875719680
author Liu, Shiyu
Shan, Lianlei
author_facet Liu, Shiyu
Shan, Lianlei
contents Recent breakthroughs in Visual Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have significantly advanced 3D scene perception towards language-driven cognition. However, existing 3D language models struggle with sparse, large-scale point clouds due to slow feature extraction and limited representation accuracy. To address these challenges, we propose NeuroVoxel-LM, a novel framework that integrates Neural Radiance Fields (NeRF) with dynamic resolution voxelization and lightweight meta-embedding. Specifically, we introduce a Dynamic Resolution Multiscale Voxelization (DR-MSV) technique that adaptively adjusts voxel granularity based on geometric and structural complexity, reducing computational cost while preserving reconstruction fidelity. In addition, we propose the Token-level Adaptive Pooling for Lightweight Meta-Embedding (TAP-LME) mechanism, which enhances semantic representation through attention-based weighting and residual fusion. Experimental results demonstrate that DR-MSV significantly improves point cloud feature extraction efficiency and accuracy, while TAP-LME outperforms conventional max-pooling in capturing fine-grained semantics from NeRF weights.
format Preprint
id arxiv_https___arxiv_org_abs_2507_20110
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NeuroVoxel-LM: Language-Aligned 3D Perception via Dynamic Voxelization and Meta-Embedding
Liu, Shiyu
Shan, Lianlei
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
I.4; I.5
Recent breakthroughs in Visual Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have significantly advanced 3D scene perception towards language-driven cognition. However, existing 3D language models struggle with sparse, large-scale point clouds due to slow feature extraction and limited representation accuracy. To address these challenges, we propose NeuroVoxel-LM, a novel framework that integrates Neural Radiance Fields (NeRF) with dynamic resolution voxelization and lightweight meta-embedding. Specifically, we introduce a Dynamic Resolution Multiscale Voxelization (DR-MSV) technique that adaptively adjusts voxel granularity based on geometric and structural complexity, reducing computational cost while preserving reconstruction fidelity. In addition, we propose the Token-level Adaptive Pooling for Lightweight Meta-Embedding (TAP-LME) mechanism, which enhances semantic representation through attention-based weighting and residual fusion. Experimental results demonstrate that DR-MSV significantly improves point cloud feature extraction efficiency and accuracy, while TAP-LME outperforms conventional max-pooling in capturing fine-grained semantics from NeRF weights.
title NeuroVoxel-LM: Language-Aligned 3D Perception via Dynamic Voxelization and Meta-Embedding
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
I.4; I.5
url https://arxiv.org/abs/2507.20110