Diffusion Guided Upsampling of Sparse Indoor LiDAR Point Clouds for Occlusion Aware Scene Reconstruction Systems

Authors

  • Claire Morel Faculty of Science and Technology, University of Gothenburg, Gothenburg, Sweden Author
  • Luca Moretti Faculty of Science and Technology, University of Gothenburg, Gothenburg, Sweden Author
  • Ren Matsuda Faculty of Science and Technology, University of Gothenburg, Gothenburg, Sweden Author

DOI:

https://doi.org/10.66525/ijictt98

Keywords:

Point Cloud Upsampling, Diffusion Models, LiDAR, Scene Reconstruction, Deep Learning

Abstract

The rapid advancement of three-dimensional scanning technologies has positioned Light Detection and Ranging as a cornerstone for indoor scene reconstruction, autonomous navigation, and spatial computing. However, raw point clouds acquired from indoor environments often suffer from severe sparsity, non-uniform density, and occlusion-induced missing regions, which severely bottleneck downstream applications. To address these critical limitations, this paper proposes a novel diffusion-guided point cloud upsampling framework specifically engineered for the high-fidelity reconstruction of complex indoor scenes. By formulating the upsampling task as a conditional generative process, our methodology leverages a denoising diffusion probabilistic model that operates directly on irregular, unordered point sets. The proposed architecture employs a hierarchical feature extraction mechanism coupled with cross-attention modules to capture both local geometric nuances and global structural topologies. The forward diffusion process systematically corrupts the underlying ground-truth dense point distribution, while the reverse generative phase progressively recovers high-resolution spatial coordinates conditioned on the sparse input geometry. Extensive experimental evaluations conducted on industry-standard indoor datasets demonstrate that our approach significantly outperforms existing optimization-based and generative adversarial network-based upsampling methods across multiple quantitative metrics and qualitative visual assessments. The proposed framework excels in preserving sharp edges, generating uniform point distributions, and avoiding clustering artifacts common in previous methodologies. 

Downloads

Download data is not yet available.

References

1. Xiao, Q., & Zhou, K. (2026). MACD: Model-Aware Contrastive Decoding via Counterfactual Data. arXiv preprint arXiv:2602.01740.

2. Deng, L., Guo, H., Bai, Y., Dai, Y., Huang, H., & Shi, Y. (2025). BrepLLM: Native Boundary Representation Understanding with Large Language Models. arXiv preprint arXiv:2512.16413.

3. Qi, Z., Yuan, Y., Ruan, X., Wang, S., Zhang, W., & Huang, Q. (2024). Collaborative debias strategy for temporal sentence grounding in video. IEEE Transactions on Circuits and Systems for Video Technology, 34(11), 10972-10986.

4. Zhang, J., Luo, H., Yang, H., Xu, X., Wu, Q., Shi, Y., ... & Wang, J. (2023). Neuraldome: A neural modeling pipeline on multi-view human-object interactions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 8834-8845).

5. Qu, W., Wang, J., Gong, Y., Huang, X., & Xiao, L. (2025). An end-to-end robust point cloud semantic segmentation network with single-step conditional diffusion models. In Proceedings of the Computer Vision and Pattern Recognition Conference (pp. 27325-27335).

6. Lv, Q., Kong, W., Li, H., Zeng, J., Qiu, Z., Qu, D., ... & Pang, J. (2025). F1: A vision-language-action model bridging understanding and generation to actions. arXiv preprint arXiv:2509.06951.

7. Yang, Y., Ma, X., Li, C., Zheng, Z., Zhang, Q., Huang, G., ... & Zhao, Q. (2021). Believe what you see: Implicit constraint approach for offline multi-agent reinforcement learning. Advances in Neural Information Processing Systems, 34, 10299-10312.

8. Zhang, Jiaquan, et al. "Lightweight llm agent memory with small language models." arXiv preprint arXiv:2604.07798 (2026).

9. Huang, H., Zhang, J., Zhang, J., Xu, J., & Wu, Q. (2020). Low-rank pairwise alignment bilinear network for few-shot fine-grained image classification. IEEE Transactions on Multimedia, 23, 1666-1680.

10. Zhou, D. (2025, December). M-VP2: Microservice-Oriented Vulnerability Patch Planning-A Cost-Aware Approachusing Multi-Agent Reinforcement Learning. In 2025 5th International Conference on Computer, Internet of Things and Control Engineering (CITCE) (pp. 248-254). IEEE.

11. Chu, Y. B., Li, J., Jia, P., Cui, J., Zhang, R., Kang, X., Lv, M., & Zhang, S. (2021). Irf1- and Egr1-activated transcription plays a key role in macrophage polarization: A multiomics sequencing study with partial validation. International immunopharmacology, 99, 108072. https://doi.org/10.1016/j.intimp.2021.108072

12. Li, Q., Luo, T., & Liao, J. (2025). Theory-inspired deep multi-view multi-label learning with incomplete views and noisy labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 20706-20715).

13. Huang, H., Kang, H., Liu, S., Salvado, O., Rakotoarivelo, T., Wang, D., & Liu, T. (2023). Paddles: Phase-amplitude spectrum disentangled early stopping for learning with noisy labels. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 16719-16730).

14. Z. Qi et al., "Self-Regulated Learning for Egocentric Video Activity Anticipation" in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 45, no. 06, pp. 6715-6730, June 2023, doi: 10.1109/TPAMI.2021.3059923.

15. Guo, Zixin, Kai Zhao, and Luyan Zhang. "InstanceRSR: Real-World Super-Resolution via Instance-Aware Representation Alignment." ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2026.

16. Wang, Juyuan, et al. "HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention Heads." arXiv preprint arXiv:2604.17237 (2026).

17. Qu, W., Shao, Y., Meng, L., Huang, X., & Xiao, L. (2024). A conditional denoising diffusion probabilistic model for point cloud upsampling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 20786-20795).

18. Agrawal, H., Huang, X., Kim, J. H., Li, Y., Ma, Y., Ning, T., & Tao, Y. (2022). Automated image processing and insight presentation. Patent / invention record. Publication date: 2022-04-05.

19. Chen, L., Jiang, X., Liu, X., & Haardt, M. (2022). Reweighted low-rank factorization with deep prior for image restoration. IEEE Transactions on Signal Processing, 70, 3514-3529.

20. Peng, Q., Zheng, C., & Chen, C. (2024). A dual-augmentor framework for domain generalization in 3d human pose estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 2240-2249).

21. Wang, C., Ke, L., Liu, X., Huang, D., Yao, J., & Chu, W. Explainable AI Analysis of Brake Control in CARLA Through Reference and Distilled Policies. Frontiers in Robotics and AI, 13, 1847808.

22. Yang, Y., Wang, Q., Li, C., Hu, H., Wu, C., Jiang, Y., ... & Xu, B. (2025, May). Fewer may be better: Enhancing offline reinforcement learning with reduced dataset. In International Conference on Learning Representations (Vol. 2025, pp. 7076-7098).

23. Tu, P., Xie, X., Ai, G., Li, Y., Huang, Y., & Zheng, Y. (2023). FemtoDet: An object detection baseline for energy versus performance tradeoffs. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 13318-13327).

24. Zhou, Yufan, et al. "Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos." arXiv preprint arXiv:2507.03393 (2025).

25. Wang, J., Wells III, W. M., Golland, P., & Zhang, M. (2018, September). Efficient laplace approximation for bayesian registration uncertainty quantification. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 880-888). Cham: Springer International Publishing.

26. Zhao, Haoyu, et al. "LSTD: Long Short-Term Temporal Diffusion for Video Generation." IEEE Transactions on Multimedia (2026).

27. Xu, X., Bowtell, J., Young, W. R., Fong, D. T., & Williams, G. K. (2025). Distinct patterns in neuromuscular adaptation to repeated perturbations in chronic ankle instability. Journal of NeuroEngineering and Rehabilitation.

28. Jiang, L., Cao, Z., Chen, W., Zheng, X., Lyu, Y., Li, Z., ... & Chen, Y. C. (2026). SAP: Segment Any 4K Panorama. arXiv preprint arXiv:2603.12759.

29. Li, Q., Luo, T., Jiang, M., Liao, J., & Jiang, Z. (2024, October). Deep incomplete multi-view network semi-supervised multi-label learning with unbiased loss. In Proceedings of the 32nd ACM International Conference on Multimedia (pp. 9048-9056).

30. Tu, P., Huang, Y., Zheng, F., He, Z., Cao, L., & Shao, L. (2022, June). Guidedmix-net: Semi-supervised semantic segmentation by using labeled images as reference. In Proceedings of the AAAI conference on artificial intelligence (Vol. 36, No. 2, pp. 2379-2387).

31. Kim, E. H., Wang, Z., Zong, H., Jiang, Z., Fu, Z., & Pedrycz, W. (2023). Design of tobacco leaves classifier through fuzzy clustering-based neural networks with multiple histogram analyses of images. IEEE Transactions on Industrial Informatics, 20(3), 4698-4709.

32. He, Y., Li, S., Li, K., Wang, J., Li, B., Shi, T., ... & Wang, X. (2025). Ge-adapter: A general and efficient adapter for enhanced video editing with pretrained text-to-image diffusion models. Expert Systems with Applications, 129649.

33. Ma, Y., Qu, D., & Pyrozhenko, M. (2026). Bio-RegNet: A Meta-Homeostatic Bayesian Neural Network Framework Integrating Treg-Inspired Immunoregulation and Autophagic Optimization for Adaptive Community Detection and Stable Intelligence. Biomimetics, 11(1), 48.

34. Zhao, C., Zhang, J., Du, J., Shan, Z., Wang, J., Yu, J., ... & Xu, L. (2024). I'm hoi: Inertia-aware monocular capture of 3d human-object interactions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 729-741).

Downloads

Published

2026-06-01