# MOSE: Monocular Semantic Reconstruction Using NeRF-Lifted Noisy Priors

arXiv: https://arxiv.org/abs/2409.14019 · HTML: https://mlsanity.com/paper/2409.14019/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 29 references that are in the map.
- First posted on arXiv 21 Sep 2024.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021)
- [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020)
- [Implicit Geometric Regularization for Learning Shapes](https://mlsanity.com/paper/2002.10099/) (2020)
- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [Panoptic Lifting for 3D Scene Understanding with Neural Fields](https://mlsanity.com/paper/2212.09802/) (2022)
- [NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors](https://mlsanity.com/paper/2206.13597/) (2022)
- [Neural 3D Scene Reconstruction with the Manhattan-world Assumption](https://mlsanity.com/paper/2205.02836/) (2022)
- [Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation](https://mlsanity.com/paper/2109.09881/) (2021)
- [PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things](https://mlsanity.com/paper/1903.01177/) (2019)
- [Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion](https://mlsanity.com/paper/2306.04633/) (2023)
- [SceneCode: Monocular Dense Semantic Reconstruction using Learned Encoded Scene Representations](https://mlsanity.com/paper/1903.06482/) (2019)
- [RICO: Regularizing the Unobservable for Indoor Compositional Reconstruction](https://mlsanity.com/paper/2303.08605/) (2023)
- [H2O-SDF: Two-phase Learning for 3D Indoor Reconstruction using Object Surface Fields](https://mlsanity.com/paper/2402.08138/) (2024)

## Built on by (most cited first, 1 of 1)

- [Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy](https://mlsanity.com/paper/2605.00719/) (2026)

## Abstract (arXiv)

Accurately reconstructing dense and semantically annotated 3D meshes from monocular images remains a challenging task due to the lack of geometry guidance and imperfect view-dependent 2D priors. Though we have witnessed recent advancements in implicit neural scene representations enabling precise 2D rendering simply from multi-view images, there have been few works addressing 3D scene understanding with monocular priors alone. In this paper, we propose MOSE, a neural field semantic reconstruction approach to lift inferred image-level noisy priors to 3D, producing accurate semantics and geometry in both 3D and 2D space. The key motivation for our method is to leverage generic class-agnostic segment masks as guidance to promote local consistency of rendered semantics during training. With the help of semantics, we further apply a smoothness regularization to texture-less regions for better geometric quality, thus achieving mutual benefits of geometry and semantics. Experiments on the ScanNet dataset show that our MOSE outperforms relevant baselines across all metrics on tasks of 3D semantic segmentation, 2D semantic segmentation and 3D surface reconstruction.