# OCCDiff: Occupancy Diffusion Model for High-Fidelity 3D Building Reconstruction from Noisy Point Clouds

arXiv: https://arxiv.org/abs/2512.08506 · HTML: https://mlsanity.com/paper/2512.08506/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 9 Dec 2025.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

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

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [MVDream: Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2308.16512/) (2023)
- [Diffusion Probabilistic Models for 3D Point Cloud Generation](https://mlsanity.com/paper/2103.01458/) (2021)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Flow Matching Guide and Code](https://mlsanity.com/paper/2412.06264/) (2024)
- [SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation](https://mlsanity.com/paper/2212.04493/) (2022)
- [PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers](https://mlsanity.com/paper/2108.08839/) (2021)
- [Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions](https://mlsanity.com/paper/2211.13757/) (2022)
- [Learning Shape Priors for Single-View 3D Completion and Reconstruction](https://mlsanity.com/paper/1809.05068/) (2018)
- [PointAttN: You Only Need Attention for Point Cloud Completion](https://mlsanity.com/paper/2203.08485/) (2022)
- [ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer](https://mlsanity.com/paper/2302.14435/) (2023)
- [Controllable Mesh Generation Through Sparse Latent Point Diffusion Models](https://mlsanity.com/paper/2303.07938/) (2023)
- [DiffComplete: Diffusion-based Generative 3D Shape Completion](https://mlsanity.com/paper/2306.16329/) (2023)
- [PolyGNN: Polyhedron-based Graph Neural Network for 3D Building Reconstruction from Point Clouds](https://mlsanity.com/paper/2307.08636/) (2023)
- [SC-Diff: 3D Shape Completion with Latent Diffusion Models](https://mlsanity.com/paper/2403.12470/) (2024)
- [Building-PCC: Building Point Cloud Completion Benchmarks](https://mlsanity.com/paper/2404.15644/) (2024)
- [APC2Mesh: Bridging the gap from occluded building faccades to full 3D models](https://mlsanity.com/paper/2404.02391/) (2024)
- [Diffusion-Occ: 3D Point Cloud Completion via Occupancy Diffusion](https://mlsanity.com/paper/2408.14846/) (2024)

## Abstract (arXiv)

A major challenge in reconstructing buildings from LiDAR point clouds lies in accurately capturing building surfaces under varying point densities and noise interference. To flexibly gather high-quality 3D profiles of the building in diverse resolution, we propose OCCDiff applying latent diffusion in the occupancy function space. Our OCCDiff combines a latent diffusion process with a function autoencoder architecture to generate continuous occupancy functions evaluable at arbitrary locations. Moreover, a point encoder is proposed to provide condition features to diffusion learning, constraint the final occupancy prediction for occupancy decoder, and insert multi-modal features for latent generation to latent encoder. To further enhance the model performance, a multi-task training strategy is employed, ensuring that the point encoder learns diverse and robust feature representations. Empirical results show that our method generates physically consistent samples with high fidelity to the target distribution and exhibits robustness to noisy data.