PointNeRF++: A multi-scale, point-based Neural Radiance Field

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sun, Weiwei, Trulls, Eduard, Tseng, Yang-Che, Sambandam, Sneha, Sharma, Gopal, Tagliasacchi, Andrea, Yi, Kwang Moo
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909145910738944
author Sun, Weiwei
Trulls, Eduard
Tseng, Yang-Che
Sambandam, Sneha
Sharma, Gopal
Tagliasacchi, Andrea
Yi, Kwang Moo
author_facet Sun, Weiwei
Trulls, Eduard
Tseng, Yang-Che
Sambandam, Sneha
Sharma, Gopal
Tagliasacchi, Andrea
Yi, Kwang Moo
contents Point clouds offer an attractive source of information to complement images in neural scene representations, especially when few images are available. Neural rendering methods based on point clouds do exist, but they do not perform well when the point cloud quality is low -- e.g., sparse or incomplete, which is often the case with real-world data. We overcome these problems with a simple representation that aggregates point clouds at multiple scale levels with sparse voxel grids at different resolutions. To deal with point cloud sparsity, we average across multiple scale levels -- but only among those that are valid, i.e., that have enough neighboring points in proximity to the ray of a pixel. To help model areas without points, we add a global voxel at the coarsest scale, thus unifying ``classical'' and point-based NeRF formulations. We validate our method on the NeRF Synthetic, ScanNet, and KITTI-360 datasets, outperforming the state of the art, with a significant gap compared to other NeRF-based methods, especially on more challenging scenes.
format Preprint
id arxiv_https___arxiv_org_abs_2312_02362
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle PointNeRF++: A multi-scale, point-based Neural Radiance Field
Sun, Weiwei
Trulls, Eduard
Tseng, Yang-Che
Sambandam, Sneha
Sharma, Gopal
Tagliasacchi, Andrea
Yi, Kwang Moo
Computer Vision and Pattern Recognition
Graphics
Point clouds offer an attractive source of information to complement images in neural scene representations, especially when few images are available. Neural rendering methods based on point clouds do exist, but they do not perform well when the point cloud quality is low -- e.g., sparse or incomplete, which is often the case with real-world data. We overcome these problems with a simple representation that aggregates point clouds at multiple scale levels with sparse voxel grids at different resolutions. To deal with point cloud sparsity, we average across multiple scale levels -- but only among those that are valid, i.e., that have enough neighboring points in proximity to the ray of a pixel. To help model areas without points, we add a global voxel at the coarsest scale, thus unifying ``classical'' and point-based NeRF formulations. We validate our method on the NeRF Synthetic, ScanNet, and KITTI-360 datasets, outperforming the state of the art, with a significant gap compared to other NeRF-based methods, especially on more challenging scenes.
title PointNeRF++: A multi-scale, point-based Neural Radiance Field
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2312.02362