Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
173 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Enhanced 3D Urban Scene Reconstruction and Point Cloud Densification using Gaussian Splatting and Google Earth Imagery (2405.11021v2)

Published 17 May 2024 in cs.CV

Abstract: 3D urban scene reconstruction and modelling is a crucial research area in remote sensing with numerous applications in academia, commerce, industry, and administration. Recent advancements in view synthesis models have facilitated photorealistic 3D reconstruction solely from 2D images. Leveraging Google Earth imagery, we construct a 3D Gaussian Splatting model of the Waterloo region centered on the University of Waterloo and are able to achieve view-synthesis results far exceeding previous 3D view-synthesis results based on neural radiance fields which we demonstrate in our benchmark. Additionally, we retrieved the 3D geometry of the scene using the 3D point cloud extracted from the 3D Gaussian Splatting model which we benchmarked against our Multi- View-Stereo dense reconstruction of the scene, thereby reconstructing both the 3D geometry and photorealistic lighting of the large-scale urban scene through 3D Gaussian Splatting

Definition Search Book Streamline Icon: https://streamlinehq.com
References (47)
  1. Alphabet Inc., 2015-2024. Google earth studio. URL: https://www.google.com/earth/studio/.
  2. Self-driving cars: A survey. Expert systems with applications 165, 113816.
  3. Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 5855–5864.
  4. Mip-nerf 360: Unbounded anti-aliased neural radiance fields, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5470–5479.
  5. Method for registration of 3-d shapes, in: Sensor fusion IV: control paradigms and data structures, Spie. pp. 586–606.
  6. Applications of 3d city models: State of the art review. ISPRS International Journal of Geo-Information 4, 2842–2889.
  7. Markerless vision-based augmented reality for urban planning. Computer-Aided Civil and Infrastructure Engineering 29, 2–17.
  8. Tensorf: Tensorial radiance fields, in: European Conference on Computer Vision, Springer. pp. 333–350.
  9. Shadow neural radiance fields for multi-view satellite photogrammetry, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1152–1161.
  10. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM 24, 381–395.
  11. Plenoxels: Radiance fields without neural networks, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5501–5510.
  12. Nerf: Neural radiance field in 3d vision, a comprehensive review. arXiv preprint arXiv:2210.00379 .
  13. Multiple view geometry in computer vision. Cambridge university press.
  14. Large scale multi-view stereopsis evaluation, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 406–413.
  15. Screened poisson surface reconstruction. ACM Transactions on Graphics (ToG) 32, 1–13.
  16. 3d gaussian splatting for real-time radiance field rendering. ACM Transactions on Graphics 42, 1–14.
  17. A hierarchical 3d gaussian representation for real-time rendering of very large datasets. ACM Transactions on Graphics 44.
  18. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 .
  19. Digital geotwin vienna: Towards a digital twin city as geodata hub.
  20. High completeness multi-view stereo for dense reconstruction of large-scale urban scenes. ISPRS Journal of Photogrammetry and Remote Sensing 209, 173–196.
  21. 3d model generation using oblique images acquired by uav. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 42, 107–115.
  22. Object recognition from local scale-invariant features, in: Proceedings of the seventh IEEE international conference on computer vision, Ieee. pp. 1150–1157.
  23. Sat-nerf: Learning multi-view satellite photogrammetry with transient objects and shadow modeling using rpc cameras, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1311–1321.
  24. Nerf in the wild: Neural radiance fields for unconstrained photo collections, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7210–7219.
  25. Nerf: Representing scenes as neural radiance fields for view synthesis. Communications of the ACM 65, 99–106.
  26. Instant neural graphics primitives with a multiresolution hash encoding. ACM transactions on graphics (TOG) 41, 1–15.
  27. A survey of urban reconstruction, in: Computer graphics forum, Wiley Online Library. pp. 146–177.
  28. Digital pictures: representation, compression, and standards. Springer.
  29. Use of sfm-mvs approach to nadir and oblique images generated throught aerial cameras to build 2.5 d map and 3d models in urban areas. Geocarto International 37, 120–141.
  30. Urban radiance fields, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12932–12942.
  31. Visualization of urban development 3d layout plans with augmented reality. Results in Engineering 14, 100447.
  32. Three-dimensional urban flood inundation simulation based on digital aerial photogrammetry. Journal of Hydrology 584, 124308.
  33. Structure-from-motion revisited, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4104–4113.
  34. Pixelwise view selection for unstructured multi-view stereo, in: Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III 14, Springer. pp. 501–518.
  35. The digital twin of the city of zurich for urban planning. PFG–Journal of Photogrammetry, Remote Sensing and Geoinformation Science 88, 99–112.
  36. Statistics Canada, 2023. 2021 census of population. Statistics Canada Catalogue URL: https://www12.statcan.gc.ca/census-recensement/2021/dp-pd/prof/index.cfm?Lang=E.
  37. Block-nerf: Scalable large scene neural view synthesis, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8248–8258.
  38. Oblique photogrammetry supporting 3d urban reconstruction of complex scenarios. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 42, 519–526.
  39. Bundle adjustment—a modern synthesis, in: Vision Algorithms: Theory and Practice: International Workshop on Vision Algorithms Corfu, Greece, September 21–22, 1999 Proceedings, Springer. pp. 298–372.
  40. Mega-nerf: Scalable construction of large-scale nerfs for virtual fly-throughs, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12922–12931.
  41. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13, 600–612.
  42. Bungeenerf: Progressive neural radiance field for extreme multi-scale scene rendering, in: European conference on computer vision, Springer. pp. 106–122.
  43. 3d city modelling with oblique photogrammetry method. Procedia Technology 19, 424–431.
  44. Plenoctrees for real-time rendering of neural radiance fields, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 5752–5761.
  45. The unreasonable effectiveness of deep features as a perceptual metric, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 586–595.
  46. Patchmatch based joint view selection and depthmap estimation, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1510–1517.
  47. Hugs: Holistic urban 3d scene understanding via gaussian splatting. arXiv preprint arXiv:2403.12722 .

Summary

We haven't generated a summary for this paper yet.

X Twitter Logo Streamline Icon: https://streamlinehq.com