Smart City Gnosys
Smart city article details
| Title | Dense 3D Model Reconstruction For Digital City Using Computationally Efficient Multi-View Stereo Networks |
|---|---|
| ID_Doc | 18319 |
| Authors | Hu Y.; Liu Z.; Fu T.; Pun M.-O. |
| Year | 2022 |
| Published | International Geoscience and Remote Sensing Symposium (IGARSS), 2022-July |
| DOI | http://dx.doi.org/10.1109/IGARSS46834.2022.9883484 |
| Abstract | Deep learning has shown promising results on dense three-dimensional (3D) model reconstruction from RGB images in recent years. However, the reconstruction of large-scale 3D models required for digital city remains very challenging even for such deep learning based methods. In this paper, we propose a convolutional neural network (CNN)-based Multi-View-Stereo (MVS) method that uses a double U-Net approach searching for image features. The proposed network first utilizes a double U-Net to extract the image features of a coarser resolution for the sake of reduced memory requirements. After that, the cost volume is built via the differentiable homography warping. The cascade structure is designed to extract the information in a small-scale cost volume before a large-scale cost volume carries out fusion and finer depth map estimation. As a result, the proposed network can efficiently produce highly accurate 3D point clouds using a fraction of the GPU memory and runtime required by conventional methods. Extensive experiments on the DTU benchmarks as well as the Tanks and Temples benchmarks confirm that the proposed network can achieve outstanding reconstruction accuracy and model completeness. © 2022 IEEE. |
| Author Keywords |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
138  | 0.9 | Hu Y.; Fu T.; Niu G.; Liu Z.; Pun M.-O. | 3D Map Reconstruction Using A Monocular Camera For Smart Cities | Journal of Supercomputing, 78, 14 (2022) |
| 13602 | 0.889 | Akhavi Zadegan A.; Vivet D.; Hadachi A. | Challenges And Advancements In Image-Based 3D Reconstruction Of Large-Scale Urban Environments: A Review Of Deep Learning And Classical Methods | Frontiers in Computer Science, 7 (2025) |
| 11047 | 0.879 | Sun P.; Wu S.; Lin K. | Attention-Guided Multi-View Stereo Network For Depth Estimation | Proceedings - 2020 IEEE 22nd International Conference on High Performance Computing and Communications, IEEE 18th International Conference on Smart City and IEEE 6th International Conference on Data Science and Systems, HPCC-SmartCity-DSS 2020 (2020) |
| 34745 | 0.861 | Luo H.; Zhang J.; Liu X.; Zhang L.; Liu J. | Large-Scale 3D Reconstruction From Multi-View Imagery: A Comprehensive Review | Remote Sensing, 16, 5 (2024) |
| 186 | 0.856 | Cheolhwan K.; Youngmok K.; Wonjun C.; Eunkwan L.; Hong-Gyoo S. | 3D Urban Building Reconstruction Through Neural Rendering And Uav Imagery | Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, 41, 5 (2023) |
| 748 | 0.852 | Chen X.; Cheng Y.; Han X.; Zhao B.; Tao W.; Ozdemir E.; Pan D. | A Compact Surface Reconstruction Method For Buildings Based On Convolutional Neural Network Fitting Implicit Representations | Journal of Computing in Civil Engineering, 39, 3 (2025) |