# SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1609.05130 · HTML: https://mlsanity.com/paper/1609.05130/

## Key facts

- Cited by 135 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2016.

## Built on by (most cited first, 30 of 135)

- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023)
- [Visual Language Maps for Robot Navigation](https://mlsanity.com/paper/2210.05714/) (2022)
- [ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning](https://mlsanity.com/paper/2309.16650/) (2023)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)
- [Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations](https://mlsanity.com/paper/2209.03494/) (2022)
- [SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences](https://mlsanity.com/paper/2103.14898/) (2021)
- [ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields](https://mlsanity.com/paper/2211.11704/) (2022)
- [Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs](https://mlsanity.com/paper/2101.06894/) (2021)
- [NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes](https://mlsanity.com/paper/2111.13260/) (2021)
- [Bidirectional Projection Network for Cross Dimension Scene Understanding](https://mlsanity.com/paper/2103.14326/) (2021)
- [OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data](https://mlsanity.com/paper/2311.02873/) (2023)
- [Object-Compositional Neural Implicit Surfaces](https://mlsanity.com/paper/2207.09686/) (2022)
- [Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion](https://mlsanity.com/paper/2306.04633/) (2023)
- [Learning 3D Semantic Segmentation with only 2D Image Supervision](https://mlsanity.com/paper/2110.11325/) (2021)
- [ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hints](https://mlsanity.com/paper/2202.11271/) (2022)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems](https://mlsanity.com/paper/2106.14386/) (2021)
- [Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks](https://mlsanity.com/paper/2108.01176/) (2021)
- [SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency](https://mlsanity.com/paper/2112.01001/) (2021)
- [3D-Aware Object Goal Navigation via Simultaneous Exploration and Identification](https://mlsanity.com/paper/2212.00338/) (2022)
- [Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation from 2D Supervision](https://mlsanity.com/paper/2303.03361/) (2023)
- [SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation](https://mlsanity.com/paper/2311.17707/) (2023)
- [When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models](https://mlsanity.com/paper/2405.10255/) (2024)
- [SemGauss-SLAM: Dense Semantic Gaussian Splatting SLAM](https://mlsanity.com/paper/2403.07494/) (2024)
- [EmbodiedSAM: Online Segment Any 3D Thing in Real Time](https://mlsanity.com/paper/2408.11811/) (2024)
- [Incremental 3D Semantic Scene Graph Prediction from RGB Sequences](https://mlsanity.com/paper/2305.02743/) (2023)
- [LaTeRF: Label and Text Driven Object Radiance Fields](https://mlsanity.com/paper/2207.01583/) (2022)
- [Feature-Realistic Neural Fusion for Real-Time, Open Set Scene Understanding](https://mlsanity.com/paper/2210.03043/) (2022)

## Abstract (arXiv)

Ever more robust, accurate and detailed mapping using visual sensing has proven to be an enabling factor for mobile robots across a wide variety of applications. For the next level of robot intelligence and intuitive user interaction, maps need extend beyond geometry and appearence - they need to contain semantics. We address this challenge by combining Convolutional Neural Networks (CNNs) and a state of the art dense Simultaneous Localisation and Mapping (SLAM) system, ElasticFusion, which provides long-term dense correspondence between frames of indoor RGB-D video even during loopy scanning trajectories. These correspondences allow the CNN's semantic predictions from multiple view points to be probabilistically fused into a map. This not only produces a useful semantic 3D map, but we also show on the NYUv2 dataset that fusing multiple predictions leads to an improvement even in the 2D semantic labelling over baseline single frame predictions. We also show that for a smaller reconstruction dataset with larger variation in prediction viewpoint, the improvement over single frame segmentation increases. Our system is efficient enough to allow real-time interactive use at frame-rates of approximately 25Hz.