发表机构
College of Electronics and Information Engineering, Shenzhen University; Guangdong Key Laboratory of Intelligent Information Processing（深圳大学电子与信息工程学院; 广东省智能信息处理重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对室内语义占用预测的长尾类别瓶颈，提出Group-UFD Occ方法，通过分组策略与UFD损失优化，在EmbodiedScan数据集上较基线实现11.38%相对提升，长尾类别精度显著提高。
AI 中文摘要
近年来，3D语义占用预测因用于理解室内场景而受到越来越多关注。但与结构化的室外环境不同，室内场景具有类别多样性高且呈现严重长尾分布的特点，这已成为限制现有模型性能的核心瓶颈。为解决该挑战，我们提出一种基于分层语义监督与协同损失优化的新方法Group-UFD Occ。在架构层面，我们引入细粒度语义分组策略，并设计多尺度并行的“主专家”预测头，通过深度正则化引导模型高效学习尾类特征；在优化层面，我们引入统一焦点-骰子（Unified Focal-Dice, UFD）损失，该协同损失函数会在每个体素层面动态聚焦难样本，同时从基于区域的视角同步优化预测物体的几何完整性。我们在大规模EmbodiedScan数据集上开展实验，结果表明，与基线相比，该方法实现了11.38%的相对提升，且在多个关键长尾类别上取得了显著的精度增益。
英文摘要
Recently, 3D semantic occupancy prediction has garnered increasing attention for understanding the indoor scene. However, unlike structured outdoor environments, indoor scenes feature a high diversity of object categories that exhibit a severe long-tailed distribution, which has become a core bottleneck limiting the performance of existing models. To tackle this challenge, we propose a novel method, Group-UFD Occ, based on hierarchical semantic supervision and synergistic loss optimization. At the architectural level, we introduce a fine-grained semantic grouping strategy and design multi-scale, parallel ``main-expert'' prediction heads to guide the model in efficiently learning tail-class features through deep regularization. At the optimization level, we introduce the Unified Focal-Dice (UFD) loss. This synergistic loss function dynamically focuses on hard samples at the per-voxel level. Meanwhile, it simultaneously optimizes the geometric integrity of predicted objects from a region-based perspective. We conducted experiments on the large-scale EmbodiedScan dataset. The results demonstrate that our method yields a relative improvement of 11.38\% over the baseline, with substantial accuracy gains in several critical long-tailed categories.
Comments8 pages, 2 figures
