INGeo: Accelerating Instant Neural Scene Reconstruction with Noisy Geometry Priors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Chaojian, Wu, Bichen, Pumarola, Albert, Zhang, Peizhao, Lin, Yingyan Celine, Vajda, Peter
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908287578931200
author Li, Chaojian
Wu, Bichen
Pumarola, Albert
Zhang, Peizhao
Lin, Yingyan Celine
Vajda, Peter
author_facet Li, Chaojian
Wu, Bichen
Pumarola, Albert
Zhang, Peizhao
Lin, Yingyan Celine
Vajda, Peter
contents We present a method that accelerates reconstruction of 3D scenes and objects, aiming to enable instant reconstruction on edge devices such as mobile phones and AR/VR headsets. While recent works have accelerated scene reconstruction training to minute/second-level on high-end GPUs, there is still a large gap to the goal of instant training on edge devices which is yet highly desired in many emerging applications such as immersive AR/VR. To this end, this work aims to further accelerate training by leveraging geometry priors of the target scene. Our method proposes strategies to alleviate the noise of the imperfect geometry priors to accelerate the training speed on top of the highly optimized Instant-NGP. On the NeRF Synthetic dataset, our work uses half of the training iterations to reach an average test PSNR of >30.
format Preprint
id arxiv_https___arxiv_org_abs_2212_01959
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle INGeo: Accelerating Instant Neural Scene Reconstruction with Noisy Geometry Priors
Li, Chaojian
Wu, Bichen
Pumarola, Albert
Zhang, Peizhao
Lin, Yingyan Celine
Vajda, Peter
Computer Vision and Pattern Recognition
We present a method that accelerates reconstruction of 3D scenes and objects, aiming to enable instant reconstruction on edge devices such as mobile phones and AR/VR headsets. While recent works have accelerated scene reconstruction training to minute/second-level on high-end GPUs, there is still a large gap to the goal of instant training on edge devices which is yet highly desired in many emerging applications such as immersive AR/VR. To this end, this work aims to further accelerate training by leveraging geometry priors of the target scene. Our method proposes strategies to alleviate the noise of the imperfect geometry priors to accelerate the training speed on top of the highly optimized Instant-NGP. On the NeRF Synthetic dataset, our work uses half of the training iterations to reach an average test PSNR of >30.
title INGeo: Accelerating Instant Neural Scene Reconstruction with Noisy Geometry Priors
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2212.01959