Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Guo, Wenxuan, Xu, Xiuwei, Wang, Ziwei, Feng, Jianjiang, Zhou, Jie, Lu, Jiwen
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2502.10392
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909533469671424
author Guo, Wenxuan
Xu, Xiuwei
Wang, Ziwei
Feng, Jianjiang
Zhou, Jie
Lu, Jiwen
author_facet Guo, Wenxuan
Xu, Xiuwei
Wang, Ziwei
Feng, Jianjiang
Zhou, Jie
Lu, Jiwen
contents In this paper, we propose an efficient multi-level convolution architecture for 3D visual grounding. Conventional methods are difficult to meet the requirements of real-time inference due to the two-stage or point-based architecture. Inspired by the success of multi-level fully sparse convolutional architecture in 3D object detection, we aim to build a new 3D visual grounding framework following this technical route. However, as in 3D visual grounding task the 3D scene representation should be deeply interacted with text features, sparse convolution-based architecture is inefficient for this interaction due to the large amount of voxel features. To this end, we propose text-guided pruning (TGP) and completion-based addition (CBA) to deeply fuse 3D scene representation and text features in an efficient way by gradual region pruning and target completion. Specifically, TGP iteratively sparsifies the 3D scene representation and thus efficiently interacts the voxel features with text features by cross-attention. To mitigate the affect of pruning on delicate geometric information, CBA adaptively fixes the over-pruned region by voxel completion with negligible computational overhead. Compared with previous single-stage methods, our method achieves top inference speed and surpasses previous fastest method by 100\% FPS. Our method also achieves state-of-the-art accuracy even compared with two-stage methods, with $+1.13$ lead of Acc@0.5 on ScanRefer, and $+2.6$ and $+3.2$ leads on NR3D and SR3D respectively. The code is available at \href{https://github.com/GWxuan/TSP3D}{https://github.com/GWxuan/TSP3D}.
format Preprint
id arxiv_https___arxiv_org_abs_2502_10392
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TSP3D: Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding
Guo, Wenxuan
Xu, Xiuwei
Wang, Ziwei
Feng, Jianjiang
Zhou, Jie
Lu, Jiwen
Computer Vision and Pattern Recognition
Machine Learning
In this paper, we propose an efficient multi-level convolution architecture for 3D visual grounding. Conventional methods are difficult to meet the requirements of real-time inference due to the two-stage or point-based architecture. Inspired by the success of multi-level fully sparse convolutional architecture in 3D object detection, we aim to build a new 3D visual grounding framework following this technical route. However, as in 3D visual grounding task the 3D scene representation should be deeply interacted with text features, sparse convolution-based architecture is inefficient for this interaction due to the large amount of voxel features. To this end, we propose text-guided pruning (TGP) and completion-based addition (CBA) to deeply fuse 3D scene representation and text features in an efficient way by gradual region pruning and target completion. Specifically, TGP iteratively sparsifies the 3D scene representation and thus efficiently interacts the voxel features with text features by cross-attention. To mitigate the affect of pruning on delicate geometric information, CBA adaptively fixes the over-pruned region by voxel completion with negligible computational overhead. Compared with previous single-stage methods, our method achieves top inference speed and surpasses previous fastest method by 100\% FPS. Our method also achieves state-of-the-art accuracy even compared with two-stage methods, with $+1.13$ lead of Acc@0.5 on ScanRefer, and $+2.6$ and $+3.2$ leads on NR3D and SR3D respectively. The code is available at \href{https://github.com/GWxuan/TSP3D}{https://github.com/GWxuan/TSP3D}.
title TSP3D: Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2502.10392