3D Reconstruction using Machine Learning / (Record no. 613797)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 02144nam a22001577a 4500 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 629.8 |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Iqra Asghar |
| 245 ## - TITLE STATEMENT | |
| Title | 3D Reconstruction using Machine Learning / |
| Statement of responsibility, etc. | Asghar, Iqra |
| 264 ## - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE | |
| Place of production, publication, distribution, manufacture | Islamabad : |
| Name of producer, publisher, distributor, manufacturer | SMME- NUST; |
| Date of production, publication, distribution, manufacture, or copyright notice | 2025 |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 84p. |
| Other physical details | Soft Copy |
| Dimensions | 30cm |
| 500 ## - GENERAL NOTE | |
| General note | The field of 3D reconstruction has undergone significant advancements with the<br/>integration of machine learning techniques, enabling more efficient and accurate modeling<br/>of complex environments. This research focuses on leveraging cutting-edge<br/>methodologies, such as 3D Gaussian Splatting, to address challenges in real-time rendering<br/>and dynamic scene reconstruction. Traditional methods for dynamic scene rendering often<br/>fall short in maintaining high-quality and real-time performance, especially for complex,<br/>moving environments. In contrast, Gaussian Splatting employs probabilistic primitives to<br/>represent 3D point clouds, offering a balance between computational efficiency and visual<br/>quality. This study extends Progressive Gaussian Splatting to dynamic environments by<br/>introducing a framework that ensures temporal coherence and real-time performance. The<br/>proposed methodology employs a hybrid geometric representation, progressive<br/>propagation for Gaussian refinement, and deformation fields encoded via multi-resolution<br/>voxel grids to capture motion. Evaluations on synthetic and real-world datasets<br/>demonstrate significant improvements in rendering quality and temporal coherence,<br/>achieving state-of-the-art results in metrics such as PSNR (41.99), SSIM (0.995), and<br/>LPIPS (0.011) for synthetic dataset and increased PSNR by 1.79 and SSIM by 0.046 for<br/>real world’s hypernerf dataset. The research provides new insights into the practical<br/>application of Gaussian Splatting in dynamic environments, opening avenues for enhanced<br/>virtual reality (VR), augmented reality (AR), and robotics applications. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | MS Robotics and Intelligent Machine Engineering |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Supervisor : Dr. Sara Baber |
| 856 ## - ELECTRONIC LOCATION AND ACCESS | |
| Uniform Resource Identifier | <a href="http://10.250.8.41:8080/xmlui/handle/123456789/52411">http://10.250.8.41:8080/xmlui/handle/123456789/52411</a> |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | |
| Koha item type | Thesis |
| Withdrawn status | Permanent Location | Current Location | Shelving location | Date acquired | Full call number | Barcode | Koha item type |
|---|---|---|---|---|---|---|---|
| School of Mechanical & Manufacturing Engineering (SMME) | School of Mechanical & Manufacturing Engineering (SMME) | E-Books | 05/21/2025 | 629.8 | SMME-TH-1130 | Thesis |