UniMapping: Unified SLAM Framework for Map-Centric Embodied Perception
Xiaze Zhang, Ziheng Ding, Yuejie Zhang, lifeng chen, Rui Feng
Abstract
Simultaneous Localization and Mapping (SLAM) is increasingly expected to provide reusable spatial representations for downstream perception. However, existing approaches often struggle with scale-consistency and producing maps that lack the geometric fidelity required for reliable perception. We propose _UniMapping_, a unified SLAM framework that constructs a persistent neural-descriptor map from multimodal observations. We introduce a **Spatial-Aware Deformable Transformer** that injects explicit geometric inductive bias to ensure scale-invariant feature extraction, alongside a **Spatial Fusion** strategy that decouples feature aggregation from temporal sequences. Extensive experiments on both indoor and outdoor benchmarks demonstrate competitive SLAM performance. Notably, our method significantly enhances downstream tasks (mAP +3.1% and mIoU +7.1%) by leveraging accumulated multi-view context.
BibTeX
@inproceedings{
zhang2026unimapping,
title={UniMapping: Unified {SLAM} Framework for Map-Centric Embodied Perception},
author={Xiaze Zhang and Ziheng Ding and Yuejie Zhang and lifeng chen and Rui Feng},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=bQkKVGuHZA}
}