发表机构
ETH Zurich; Microsoft; ETH AI Center（苏黎世联邦理工学院; 微软; 苏黎世联邦理工学院人工智能中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出基于语义熵、几何曲率和纹理丰富度的自适应体素细化框架，并引入强化学习智能体在用户指定内存预算下学习细分策略，实现更高精度和更好的内存-精度权衡。
AI 中文摘要
基于体素的体积建图是三维重建的基础，但固定分辨率的网格本质上效率低下——在均匀区域浪费内存，在复杂区域丢失细节。现有的自适应方法，如MAP-ADAPT，通过基于几何和用户定义的语义类别列表改变分辨率来部分解决这一问题，但这些启发式方法需要专家调优，缺乏对未见物体的泛化能力，并且没有提供明确的内存使用控制机制。我们提出了一种自适应框架，基于语义熵（捕捉标签不确定性）以及几何曲率和纹理丰富度作为场景复杂度线索来细化体素，从而在无需依赖语义分类学的情况下实现有原则的分辨率分配。为了使精度-内存权衡明确且用户可控，我们进一步引入了一个强化学习智能体，在用户指定的目标内存预算下学习体素细分策略，用单个直观的控制参数取代手工调整的阈值。与MAP-ADAPT和固定分辨率基线相比，所生成的多分辨率TSDF在合成和真实世界数据集上均实现了更高的几何精度、更好的语义一致性以及改进的内存-精度权衡。我们的代码和模型可在https URL获取。
英文摘要
Voxel-based volumetric mapping is fundamental to 3D reconstruction, yet fixed-resolution grids remain inherently inefficient - wasting memory in uniform regions and losing detail in complex ones. Existing adaptive methods, such as MAP-ADAPT, partially address this by varying resolution based on geometry and user-defined semantic class lists, but these heuristics require expert tuning, lack generalization to unseen objects, and provide no explicit mechanism to control memory usage. We propose an adaptive framework that refines voxels based on semantic entropy, which captures label uncertainty, together with geometric curvature and texture richness as scene complexity cues, yielding principled resolution allocation without reliance on semantic taxonomies. To make the accuracy-memory trade-off explicit and user-controlled, we further introduce a reinforcement learning agent that learns voxel subdivision policies under a user-specified target memory budget, replacing hand-tuned thresholds with a single intuitive control parameter. The resulting multi-resolution TSDF achieves higher geometric accuracy, better semantic consistency, and improved memory-accuracy trade-offs compared to MAP-ADAPT and fixed-resolution baselines on both synthetic and real-world datasets. Our code and models are available at https://github.com/alpayozkan/UnRL.
CommentsTo appear at BMVC 2026. Code available at https://github.com/alpayozkan/UnRL
