# SplitFusion: Simultaneous Tracking and Mapping for Non-Rigid Scenes

arXiv: https://arxiv.org/abs/2007.02108 · HTML: https://mlsanity.com/paper/2007.02108/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2020.

## Built on by (most cited first, 4 of 4)

- [Lepard: Learning partial point cloud matching in rigid and deformable scenes](https://mlsanity.com/paper/2111.12591/) (2021)
- [Recent Trends in 3D Reconstruction of General Non-Rigid Scenes](https://mlsanity.com/paper/2403.15064/) (2024)
- [Neural Density-Distance Fields](https://mlsanity.com/paper/2207.14455/) (2022)
- [PoseFusion2: Simultaneous Background Reconstruction and Human Shape Recovery in Real-time](https://mlsanity.com/paper/2108.00695/) (2021)

## Abstract (arXiv)

We present SplitFusion, a novel dense RGB-D SLAM framework that simultaneously performs tracking and dense reconstruction for both rigid and non-rigid components of the scene. SplitFusion first adopts deep learning based semantic instant segmentation technique to split the scene into rigid or non-rigid surfaces. The split surfaces are independently tracked via rigid or non-rigid ICP and reconstructed through incremental depth map fusion. Experimental results show that the proposed approach can provide not only accurate environment maps but also well-reconstructed non-rigid targets, e.g. the moving humans.