# Deep-SLAM++: Object-level RGBD SLAM based on class-specific deep shape priors

arXiv: https://arxiv.org/abs/1907.09691 · HTML: https://mlsanity.com/paper/1907.09691/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2019.

## Built on by (most cited first, 8 of 8)

- [SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Data](https://mlsanity.com/paper/2105.08612/) (2021)
- [DSP-SLAM: Object Oriented SLAM with Deep Shape Priors](https://mlsanity.com/paper/2108.09481/) (2021)
- [OA-SLAM: Leveraging Objects for Camera Relocalization in Visual SLAM](https://mlsanity.com/paper/2209.08338/) (2022)
- [ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Description](https://mlsanity.com/paper/2108.00355/) (2021)
- [Learning to Complete Object Shapes for Object-level Mapping in Dynamic Scenes](https://mlsanity.com/paper/2208.05067/) (2022)
- [Semantic Visual Simultaneous Localization and Mapping: A Survey](https://mlsanity.com/paper/2209.06428/) (2022)
- [Level Set-Based Camera Pose Estimation From Multiple 2D/3D Ellipse-Ellipsoid Correspondences](https://mlsanity.com/paper/2207.07953/) (2022)
- [NF-SLAM: Effective, Normalizing Flow-supported Neural Field representations for object-level visual SLAM in automotive applications](https://mlsanity.com/paper/2503.11199/) (2025)

## Abstract (arXiv)

In an effort to increase the capabilities of SLAM systems and produce object-level representations, the community increasingly investigates the imposition of higher-level priors into the estimation process. One such example is given by employing object detectors to load and register full CAD models. Our work extends this idea to environments with unknown objects and imposes object priors by employing modern class-specific neural networks to generate complete model geometry proposals. The difficulty of using such predictions in a real SLAM scenario is that the prediction performance depends on the view-point and measurement quality, with even small changes of the input data sometimes leading to a large variability in the network output. We propose a discrete selection strategy that finds the best among multiple proposals from different registered views by re-enforcing the agreement with the online depth measurements. The result is an effective object-level RGBD SLAM system that produces compact, high-fidelity, and dense 3D maps with semantic annotations. It outperforms traditional fusion strategies in terms of map completeness and resilience against degrading measurement quality.