用共享隐向量实现语义引导的回环检测，解决NeRF SLAM的累积漂移问题。
SLC$^2$-SLAM: Semantic-guided Loop Closure using Shared Latent Code for NeRF SLAM
- 复用现有NeRF系统的隐向量作为局部特征，实现高效回环检测。
- 引入语义信息优化特征聚合，提升大场景下回环识别准确率。
- 适用于复杂大场景重建，尤其在ScanNet等数据集上表现优异。
针对NeRF SLAM中严重的累积漂移问题，本文提出基于共享隐向量的语义引导回环检测方法SLC²-SLAM。我们指出，多数NeRF SLAM系统中存储的隐向量未被充分利用，仅用于提升重建质量。本文提出一种简单有效的方案，直接利用这些隐向量作为局部特征进行潜在回环检测。为进一步提升性能，从相同隐向量中解码语义信息，用于引导局部特征的聚合。检测到潜在回环后，通过图优化与捆绑调整联合优化位姿与场景重建结果。在Replica和ScanNet数据集上的大量实验表明，本方法显著优于采用预训练NetVLAD与词袋模型（Bag-of-Words）的现有NeRF SLAM方法。尤其在包含更多回环的大场景中，如ScanNet，SLC²-SLAM展现出更优的跟踪与重建效果。
原文摘要 · Abstract (English)
Targeting the notorious cumulative drift errors in NeRF SLAM, we propose a Semantic-guided Loop Closure using Shared Latent Code, dubbed SLC$^2$-SLAM. We argue that latent codes stored in many NeRF SLAM systems are not fully exploited, as they are only used for better reconstruction. In this paper, we propose a simple yet effective way to detect potential loops using the same latent codes as local features. To further improve the loop detection performance, we use the semantic information, which are also decoded from the same latent codes to guide the aggregation of local features. Finally, with the potential loops detected, we close them with a graph optimization followed by bundle adjustment to refine both the estimated poses and the reconstructed scene. To evaluate the performance of our SLC$^2$-SLAM, we conduct extensive experiments on Replica and ScanNet datasets. Our proposed semantic-guided loop closure significantly outperforms the pre-trained NetVLAD and ORB combined with Bag-of-Words, which are used in all the other NeRF SLAM with loop closure. As a result, our SLC$^2$-SLAM also demonstrated better tracking and reconstruction performance, especially in larger scenes with more loops, like ScanNet.
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。