Uni-SLAM通过不确定性感知提升室内场景重建精度与实时性
Uni-SLAM: Uncertainty-Aware Neural Implicit SLAM for Real-Time Dense Indoor Scene Reconstruction
- 用哈希网格解耦3D表示，动态调整输入数据权重
- 深度L1误差降低25%，Replica上1cm内完成率达66.86%
- 适合需要高精度薄结构重建的实时场景应用
神经隐式场因简洁性和优异性能，成为多视角表面重建的有力方法。然而，现有密集视觉SLAM系统在保持实时性的同时重建室内场景中的细长结构仍面临挑战。此前方法未考虑输入RGB-D数据质量差异，采用固定频率映射过程，导致部分帧有价值信息丢失。本文提出Uni-SLAM，一种基于哈希网格的解耦3D空间表示方法。引入新型预测不确定性以重加权损失函数，并结合局部到全局的束调整策略。在合成与真实数据集上的实验表明，本系统在保持实时性的同时达到最先进的追踪与建图精度，在Replica数据集上实现25%的深度L1误差降低，1厘米内完成率达66.86%，显著提升细结构重建效果。
原文摘要 · Abstract (English)
Neural implicit fields have recently emerged as a powerful representation method for multi-view surface reconstruction due to their simplicity and state-of-the-art performance. However, reconstructing thin structures of indoor scenes while ensuring real-time performance remains a challenge for dense visual SLAM systems. Previous methods do not consider varying quality of input RGB-D data and employ fixed-frequency mapping process to reconstruct the scene, which could result in the loss of valuable information in some frames. In this paper, we propose Uni-SLAM, a decoupled 3D spatial representation based on hash grids for indoor reconstruction. We introduce a novel defined predictive uncertainty to reweight the loss function, along with strategic local-to-global bundle adjustment. Experiments on synthetic and real-world datasets demonstrate that our system achieves state-of-the-art tracking and mapping accuracy while maintaining real-time performance. It significantly improves over current methods with a 25% reduction in depth L1 error and a 66.86% completion rate within 1 cm on the Replica dataset, reflecting a more accurate reconstruction of thin structures. Project page: https://shaoxiang777.github.io/project/uni-slam/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。