Sparsity-Aware Voxel Attention and Foreground Modulation for 3D Semantic Scene Completion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xue, Yu, Gao, Longjun, Su, Yuanqi, Lu, HaoAng, Zhang, Xiaoning
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908942794227712
author Xue, Yu
Gao, Longjun
Su, Yuanqi
Lu, HaoAng
Zhang, Xiaoning
author_facet Xue, Yu
Gao, Longjun
Su, Yuanqi
Lu, HaoAng
Zhang, Xiaoning
contents Monocular Semantic Scene Completion (SSC) aims to reconstruct complete 3D semantic scenes from a single RGB image, offering a cost-effective solution for autonomous driving and robotics. However, the inherently imbalanced nature of voxel distributions, where over 93% of voxels are empty and foreground classes are rare, poses significant challenges. Existing methods often suffer from redundant emphasis on uninformative voxels and poor generalization to long-tailed categories. To address these issues, we propose VoxSAMNet (Voxel Sparsity-Aware Modulation Network), a unified framework that explicitly models voxel sparsity and semantic imbalance. Our approach introduces: (1) a Dummy Shortcut for Feature Refinement (DSFR) module that bypasses empty voxels via a shared dummy node while refining occupied ones with deformable attention; and (2) a Foreground Modulation Strategy combining Foreground Dropout (FD) and Text-Guided Image Filter (TGIF) to alleviate overfitting and enhance class-relevant features. Extensive experiments on the public benchmarks SemanticKITTI and SSCBench-KITTI-360 demonstrate that VoxSAMNet achieves state-of-the-art performance, surpassing prior monocular and stereo baselines with mIoU scores of 18.2% and 20.2%, respectively. Our results highlight the importance of sparsity-aware and semantics-guided design for efficient and accurate 3D scene completion, offering a promising direction for future research.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05780
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Sparsity-Aware Voxel Attention and Foreground Modulation for 3D Semantic Scene Completion
Xue, Yu
Gao, Longjun
Su, Yuanqi
Lu, HaoAng
Zhang, Xiaoning
Computer Vision and Pattern Recognition
Monocular Semantic Scene Completion (SSC) aims to reconstruct complete 3D semantic scenes from a single RGB image, offering a cost-effective solution for autonomous driving and robotics. However, the inherently imbalanced nature of voxel distributions, where over 93% of voxels are empty and foreground classes are rare, poses significant challenges. Existing methods often suffer from redundant emphasis on uninformative voxels and poor generalization to long-tailed categories. To address these issues, we propose VoxSAMNet (Voxel Sparsity-Aware Modulation Network), a unified framework that explicitly models voxel sparsity and semantic imbalance. Our approach introduces: (1) a Dummy Shortcut for Feature Refinement (DSFR) module that bypasses empty voxels via a shared dummy node while refining occupied ones with deformable attention; and (2) a Foreground Modulation Strategy combining Foreground Dropout (FD) and Text-Guided Image Filter (TGIF) to alleviate overfitting and enhance class-relevant features. Extensive experiments on the public benchmarks SemanticKITTI and SSCBench-KITTI-360 demonstrate that VoxSAMNet achieves state-of-the-art performance, surpassing prior monocular and stereo baselines with mIoU scores of 18.2% and 20.2%, respectively. Our results highlight the importance of sparsity-aware and semantics-guided design for efficient and accurate 3D scene completion, offering a promising direction for future research.
title Sparsity-Aware Voxel Attention and Foreground Modulation for 3D Semantic Scene Completion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.05780