面向三维语义场景补全的稀疏性感知体素注意力与前景调制
Sparsity-Aware Voxel Attention and Foreground Modulation for 3D Semantic Scene Completion
用共享 dummy 节点跳过空体素、只对占用体素做可变形注意力，是单目 3D 重建中处理 >93% 空体素的高效注意力设计，可直接迁移到 NeRF/体素/占据预测类任务；Foreground Dropout 与文本引导图像滤波为长尾语义类别提供了一种免重采样的调制思路。
原文依据 a Dummy Shortcut for Feature Refinement (DSFR) module that bypasses empty voxels via a shared dummy node while refining occupied ones with deformable attention
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论单目语义场景补全（SSC）旨在从单张 RGB 图像重建完整的三维语义场景，为自动驾驶与机器人提供一种低成本的解决方案。然而，体素分布本身固有的不均衡性——超过 93% 的体素为空、前景类别稀少——带来了显著挑战。现有方法往往对无信息体素产生冗余关注，且对长尾类别的泛化能力较差。为解决这些问题，我们提出 VoxSAMNet（体素稀疏性感知调制网络），一个显式建模体素稀疏性与语义不均衡的统一框架。我们的方法引入：(1) 用于特征精炼的虚拟捷径（DSFR）模块，通过一个共享虚拟节点绕过空体素，同时以可变形注意力精炼被占用体素；(2) 前景调制策略，结合前景丢弃（FD）与文本引导图像滤波（TGIF），以缓解过拟合并增强与类别相关的特征。在公开基准 SemanticKITTI 与 SSCBench-KITTI-360 上的大量实验表明，VoxSAMNet 取得了最优性能，分别以 18.2% 与 20.2% 的平均交并比超越此前的单目与双目基线。我们的结果凸显了稀疏性感知与语义引导设计对于高效、准确的三维场景补全的重要性，为未来研究提供了有前景的方向。
英文原文摘要 1441 字符
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; (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.