DistGrid: Scalable Scene Reconstruction with Distributed Multi-resolution Hash Grid

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Sidun, Qiao, Peng, Ye, Zongxin, Li, Wenyu, Dou, Yong
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917660968615936
author Liu, Sidun
Qiao, Peng
Ye, Zongxin
Li, Wenyu
Dou, Yong
author_facet Liu, Sidun
Qiao, Peng
Ye, Zongxin
Li, Wenyu
Dou, Yong
contents Neural Radiance Field~(NeRF) achieves extremely high quality in object-scaled and indoor scene reconstruction. However, there exist some challenges when reconstructing large-scale scenes. MLP-based NeRFs suffer from limited network capacity, while volume-based NeRFs are heavily memory-consuming when the scene resolution increases. Recent approaches propose to geographically partition the scene and learn each sub-region using an individual NeRF. Such partitioning strategies help volume-based NeRF exceed the single GPU memory limit and scale to larger scenes. However, this approach requires multiple background NeRF to handle out-of-partition rays, which leads to redundancy of learning. Inspired by the fact that the background of current partition is the foreground of adjacent partition, we propose a scalable scene reconstruction method based on joint Multi-resolution Hash Grids, named DistGrid. In this method, the scene is divided into multiple closely-paved yet non-overlapped Axis-Aligned Bounding Boxes, and a novel segmented volume rendering method is proposed to handle cross-boundary rays, thereby eliminating the need for background NeRFs. The experiments demonstrate that our method outperforms existing methods on all evaluated large-scale scenes, and provides visually plausible scene reconstruction. The scalability of our method on reconstruction quality is further evaluated qualitatively and quantitatively.
format Preprint
id arxiv_https___arxiv_org_abs_2405_04416
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DistGrid: Scalable Scene Reconstruction with Distributed Multi-resolution Hash Grid
Liu, Sidun
Qiao, Peng
Ye, Zongxin
Li, Wenyu
Dou, Yong
Computer Vision and Pattern Recognition
Neural Radiance Field~(NeRF) achieves extremely high quality in object-scaled and indoor scene reconstruction. However, there exist some challenges when reconstructing large-scale scenes. MLP-based NeRFs suffer from limited network capacity, while volume-based NeRFs are heavily memory-consuming when the scene resolution increases. Recent approaches propose to geographically partition the scene and learn each sub-region using an individual NeRF. Such partitioning strategies help volume-based NeRF exceed the single GPU memory limit and scale to larger scenes. However, this approach requires multiple background NeRF to handle out-of-partition rays, which leads to redundancy of learning. Inspired by the fact that the background of current partition is the foreground of adjacent partition, we propose a scalable scene reconstruction method based on joint Multi-resolution Hash Grids, named DistGrid. In this method, the scene is divided into multiple closely-paved yet non-overlapped Axis-Aligned Bounding Boxes, and a novel segmented volume rendering method is proposed to handle cross-boundary rays, thereby eliminating the need for background NeRFs. The experiments demonstrate that our method outperforms existing methods on all evaluated large-scale scenes, and provides visually plausible scene reconstruction. The scalability of our method on reconstruction quality is further evaluated qualitatively and quantitatively.
title DistGrid: Scalable Scene Reconstruction with Distributed Multi-resolution Hash Grid
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.04416