arXiv：cs.LG（机器学习，全量分类）· Alpay Ozkan, Tunc Ozan Aydin, Marc Pollefeys, Jelena Trisovic, Daniel Barath·· 14 小时前AI 评分34
基于语义熵与强化学习的自适应 3D 建图框架
Uncertainty-Aware RL-Controlled Adaptive 3D Mapping
AI 导读
研究者提出一种基于语义熵、几何曲率和纹理丰富度的自适应体素细化框架，无需依赖语义分类体系即可分配分辨率。该框架引入强化学习智能体，在用户指定的目标内存预算下学习体素细分策略，用单一控制参数替代手工调参阈值。其多分辨率 TSDF 在合成与真实数据集上的几何精度、语义一致性和内存-精度权衡均优于 MAP-ADAPT 与固定分辨率基线，代码与模型已公开，论文将发表于 BMVC 2026。
正文
Abstract: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 this https URL.
| Comments: | To appear at BMVC 2026. Code available at this https URL |
| Subjects: | Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR); Image and Video Processing (eess.IV) |
| Cite as: | arXiv:2610.00188 [cs.LG] |
| (or arXiv:2610.00188v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00188 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Alpay Ozkan [view email]
[v1]
Thu, 17 Sep 2026 17:53:51 UTC (17,143 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org