# MagicRoad: Semantic-Aware 3D Road Surface Reconstruction via Obstacle Inpainting

arXiv: https://arxiv.org/abs/2507.23340 · HTML: https://mlsanity.com/paper/2507.23340/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 31 Jul 2025.

## Builds on (most cited first, 25 of 25)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](https://mlsanity.com/paper/2112.10703/) (2021)
- [Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields](https://mlsanity.com/paper/2312.03203/) (2023)
- [Large Scale Image Completion via Co-Modulated Generative Adversarial Networks](https://mlsanity.com/paper/2103.10428/) (2021)
- [ProPainter: Improving Propagation and Transformer for Video Inpainting](https://mlsanity.com/paper/2309.03897/) (2023)
- [HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting](https://mlsanity.com/paper/2403.12722/) (2024)
- [High-Fidelity Pluralistic Image Completion with Transformers](https://mlsanity.com/paper/2103.14031/) (2021)
- [Deep Flow-Guided Video Inpainting](https://mlsanity.com/paper/1905.02884/) (2019)
- [Deep Video Inpainting](https://mlsanity.com/paper/1905.01639/) (2019)
- [DiffuEraser: A Diffusion Model for Video Inpainting](https://mlsanity.com/paper/2501.10018/) (2025)
- [NeRFiller: Completing Scenes via Generative 3D Inpainting](https://mlsanity.com/paper/2312.04560/) (2023)
- [Video Inpainting of Complex Scenes](https://mlsanity.com/paper/1503.05528/) (2015)
- [Road surface 3d reconstruction based on dense subpixel disparity map estimation](https://mlsanity.com/paper/1807.01874/) (2018)
- [Occlusion-Aware Video Object Inpainting](https://mlsanity.com/paper/2108.06765/) (2021)
- [ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors](https://mlsanity.com/paper/2210.05950/) (2022)
- [RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation](https://mlsanity.com/paper/2306.11368/) (2023)
- [VORNet: Spatio-temporally Consistent Video Inpainting for Object Removal](https://mlsanity.com/paper/1904.06726/) (2019)
- [LDMapNet-U: An End-to-End System for City-Scale Lane-Level Map Updating](https://mlsanity.com/paper/2501.02763/) (2025)
- [DuMapNet: An End-to-End Vectorization System for City-Scale Lane-Level Map Generation](https://mlsanity.com/paper/2406.14255/) (2024)

## Abstract (arXiv)

Road surface reconstruction is essential for autonomous driving, supporting centimeter-accurate lane perception and high-definition mapping in complex urban environments.While recent methods based on mesh rendering or 3D Gaussian splatting (3DGS) achieve promising results under clean and static conditions, they remain vulnerable to occlusions from dynamic agents, visual clutter from static obstacles, and appearance degradation caused by lighting and weather changes. We present a robust reconstruction framework that integrates occlusion-aware 2D Gaussian surfels with semantic-guided color enhancement to recover clean, consistent road surfaces. Our method leverages a planar-adapted Gaussian representation for efficient large-scale modeling, employs segmentation-guided video inpainting to remove both dynamic and static foreground objects, and enhances color coherence via semantic-aware correction in HSV space. Extensive experiments on urban-scale datasets demonstrate that our framework produces visually coherent and geometrically faithful reconstructions, significantly outperforming prior methods under real-world conditions.