Adaptive Grids for Neural Scene Representation
| dc.contributor.author | Pajoum, Barbod | en_US |
| dc.contributor.author | Fox, Gereon | en_US |
| dc.contributor.author | Elgharib, Mohamed | en_US |
| dc.contributor.author | Habermann, Marc | en_US |
| dc.contributor.author | Theobalt, Christian | en_US |
| dc.contributor.editor | Linsen, Lars | en_US |
| dc.contributor.editor | Thies, Justus | en_US |
| dc.date.accessioned | 2024-09-09T05:27:01Z | |
| dc.date.available | 2024-09-09T05:27:01Z | |
| dc.date.issued | 2024 | |
| dc.description.abstract | We introduce a novel versatile approach to enhance the quality of grid-based neural scene representations. Grid-based scene representations model a scene by storing density and color features at discrete 3D points, which offers faster training and rendering than purely implicit methods such as NeRF. However, they require high-resolution grids to achieve high-quality outputs, leading to a significant increase in memory usage. Common standard grids with uniform voxel sizes do not account for the varying complexity of different regions within a scene. This is particularly evident when a highly detailed region or object is present, while the rest of the scene is less significant or simply empty. To address this we introduce a novel approach based on frequency domain transformations for finding the key regions in the scene and then utilize a 2-level hierarchy of grids to allocate more resources to more detailed regions. We also created a more efficient version of this concept, that adapts to a compact grid representation, namely TensoRF, which also works for very few training samples. | en_US |
| dc.description.sectionheaders | Geometry | |
| dc.description.seriesinformation | Vision, Modeling, and Visualization | |
| dc.identifier.doi | 10.2312/vmv.20241205 | |
| dc.identifier.isbn | 978-3-03868-247-9 | |
| dc.identifier.pages | 8 pages | |
| dc.identifier.uri | https://doi.org/10.2312/vmv.20241205 | |
| dc.identifier.uri | https://diglib.eg.org/handle/10.2312/vmv20241205 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.rights | Attribution 4.0 International License | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | CCS Concepts: Computing methodologies → Volumetric models; Rendering; Reconstruction | |
| dc.subject | Computing methodologies → Volumetric models | |
| dc.subject | Rendering | |
| dc.subject | Reconstruction | |
| dc.title | Adaptive Grids for Neural Scene Representation | en_US |
Files
Original bundle
1 - 1 of 1