Adaptive Grids for Neural Scene Representation

Simple item page
dc.contributor.authorPajoum, Barboden_US
dc.contributor.authorFox, Gereonen_US
dc.contributor.authorElgharib, Mohameden_US
dc.contributor.authorHabermann, Marcen_US
dc.contributor.authorTheobalt, Christianen_US
dc.contributor.editorLinsen, Larsen_US
dc.contributor.editorThies, Justusen_US
dc.date.accessioned2024-09-09T05:27:01Z
dc.date.available2024-09-09T05:27:01Z
dc.date.issued2024
dc.description.abstractWe 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.sectionheadersGeometry
dc.description.seriesinformationVision, Modeling, and Visualization
dc.identifier.doi10.2312/vmv.20241205
dc.identifier.isbn978-3-03868-247-9
dc.identifier.pages8 pages
dc.identifier.urihttps://doi.org/10.2312/vmv.20241205
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/vmv20241205
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Volumetric models; Rendering; Reconstruction
dc.subjectComputing methodologies → Volumetric models
dc.subjectRendering
dc.subjectReconstruction
dc.titleAdaptive Grids for Neural Scene Representationen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
vmv20241205.pdf
Size:
6.04 MB
Format:
Adobe Portable Document Format
Download
Collections
VMV2024