# ImpliCity: City Modeling from Satellite Images with Deep Implicit Occupancy Fields

arXiv: https://arxiv.org/abs/2201.09968 · HTML: https://mlsanity.com/paper/2201.09968/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 41 references that are in the map.
- First posted on arXiv 24 Jan 2022.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [SAL: Sign Agnostic Learning of Shapes from Raw Data](https://mlsanity.com/paper/1911.10414/) (2019)
- [Local Implicit Grid Representations for 3D Scenes](https://mlsanity.com/paper/2003.08981/) (2020)
- [Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction](https://mlsanity.com/paper/2003.10983/) (2020)
- [Learning Shape Templates with Structured Implicit Functions](https://mlsanity.com/paper/1904.06447/) (2019)
- [S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modeling](https://mlsanity.com/paper/2101.06571/) (2021)
- [Shadow Neural Radiance Fields for Multi-view Satellite Photogrammetry](https://mlsanity.com/paper/2104.09877/) (2021)
- [Reconstructing Compact Building Models from Point Clouds Using Deep Implicit Fields](https://mlsanity.com/paper/2112.13142/) (2021)
- [A New Stereo Benchmarking Dataset for Satellite Images](https://mlsanity.com/paper/1907.04404/) (2019)
- [ResDepth: A Deep Residual Prior For 3D Reconstruction From High-resolution Satellite Images](https://mlsanity.com/paper/2106.08107/) (2021)
- [Machine-learned 3D Building Vectorization from Satellite Imagery](https://mlsanity.com/paper/2104.06485/) (2021)
- [DSM Building Shape Refinement from Combined Remote Sensing Images based on Wnet-cGANs](https://mlsanity.com/paper/1903.03519/) (2019)

## Built on by (most cited first, 9 of 9)

- [PolyGNN: Polyhedron-based Graph Neural Network for 3D Building Reconstruction from Point Clouds](https://mlsanity.com/paper/2307.08636/) (2023)
- [ImplicitTerrain: a Continuous Surface Model for Terrain Data Analysis](https://mlsanity.com/paper/2406.00227/) (2024)
- [OpenCity3D: What do Vision-Language Models know about Urban Environments?](https://mlsanity.com/paper/2503.16776/) (2025)
- [APC2Mesh: Bridging the gap from occluded building faccades to full 3D models](https://mlsanity.com/paper/2404.02391/) (2024)
- [Reconstructing Building Height from Spaceborne TomoSAR Point Clouds Using a Dual-Topology Network](https://mlsanity.com/paper/2601.00658/) (2026)
- [3D detection of roof sections from a single satellite image and application to LOD2-building reconstruction](https://mlsanity.com/paper/2307.05409/) (2023)
- [Analysis of Sampling Strategies for Implicit 3D Reconstruction](https://mlsanity.com/paper/2304.03999/) (2023)
- [Refined Equivalent Pinhole Model for Large-scale 3D Reconstruction from Spaceborne CCD Imagery](https://mlsanity.com/paper/2310.20117/) (2023)
- [GridFlow: Structured Latent Flow for Seamless City-Scale 3D Point Cloud Generation](https://mlsanity.com/paper/2608.29793/) (2026)

## Abstract (arXiv)

High-resolution optical satellite sensors, combined with dense stereo algorithms, have made it possible to reconstruct 3D city models from space. However, these models are, in practice, rather noisy and tend to miss small geometric features that are clearly visible in the images. We argue that one reason for the limited quality may be a too early, heuristic reduction of the triangulated 3D point cloud to an explicit height field or surface mesh. To make full use of the point cloud and the underlying images, we introduce ImpliCity, a neural representation of the 3D scene as an implicit, continuous occupancy field, driven by learned embeddings of the point cloud and a stereo pair of ortho-photos. We show that this representation enables the extraction of high-quality DSMs: with image resolution 0.5,m, ImpliCity reaches a median height error of ≈,0.7,m and outperforms competing methods, especially w.r.t. building reconstruction, featuring intricate roof details, smooth surfaces, and straight, regular outlines.