Learning with unreliability : Fast few-shot voxel radiance fields with relative geometric consistency

We propose a voxel-based optimization framework, Re VoRF, for few-shot radiance fields that strategically ad-dress the unreliability in pseudo novel view synthesis. Our method pivots on the insight that relative depth relationships within neighboring regions are more reliable than the ab-solute colo...

Full description

Saved in:
Bibliographic Details
Main Authors: XU, Yingjie, LIU, Bangzhen, TANG, Hao, DENG, Bailin, HE, Shengfeng
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2024
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/9775
https://ink.library.smu.edu.sg/context/sis_research/article/10775/viewcontent/2403.17638v1.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-10775
record_format dspace
spelling sg-smu-ink.sis_research-107752024-12-16T02:09:55Z Learning with unreliability : Fast few-shot voxel radiance fields with relative geometric consistency XU, Yingjie LIU, Bangzhen TANG, Hao DENG, Bailin HE, Shengfeng We propose a voxel-based optimization framework, Re VoRF, for few-shot radiance fields that strategically ad-dress the unreliability in pseudo novel view synthesis. Our method pivots on the insight that relative depth relationships within neighboring regions are more reliable than the ab-solute color values in disoccluded areas. Consequently, we devise a bilateral geometric consistency loss that carefully navigates the trade-off between color fidelity and geometric accuracy in the context of depth consistency for uncertain regions. Moreover, we present a reliability-guided learning strategy to discern and utilize the variable quality across syn-thesized views, complemented by a reliability-aware voxel smoothing algorithm that smoothens the transition between reliable and unreliable data patches. Our approach allows for a more nuanced use of all available data, promoting en-hanced learning from regions previously considered unsuit-able for high-quality reconstruction. Extensive experiments across diverse datasets reveal that our approach attains significant gains in efficiency and accuracy, delivering ren-dering speeds of 3 FPS, 7 mins to train a 360° scene, and a 5% improvement in PSNR over existing few-shot methods. 2024-06-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9775 info:doi/10.1109/CVPR52733.2024.01923 https://ink.library.smu.edu.sg/context/sis_research/article/10775/viewcontent/2403.17638v1.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Computer vision Accuracy Smoothing methods Codes Image color analysis Navigation Pattern recognition Artificial Intelligence and Robotics Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Computer vision
Accuracy
Smoothing methods
Codes
Image color analysis
Navigation
Pattern recognition
Artificial Intelligence and Robotics
Graphics and Human Computer Interfaces
spellingShingle Computer vision
Accuracy
Smoothing methods
Codes
Image color analysis
Navigation
Pattern recognition
Artificial Intelligence and Robotics
Graphics and Human Computer Interfaces
XU, Yingjie
LIU, Bangzhen
TANG, Hao
DENG, Bailin
HE, Shengfeng
Learning with unreliability : Fast few-shot voxel radiance fields with relative geometric consistency
description We propose a voxel-based optimization framework, Re VoRF, for few-shot radiance fields that strategically ad-dress the unreliability in pseudo novel view synthesis. Our method pivots on the insight that relative depth relationships within neighboring regions are more reliable than the ab-solute color values in disoccluded areas. Consequently, we devise a bilateral geometric consistency loss that carefully navigates the trade-off between color fidelity and geometric accuracy in the context of depth consistency for uncertain regions. Moreover, we present a reliability-guided learning strategy to discern and utilize the variable quality across syn-thesized views, complemented by a reliability-aware voxel smoothing algorithm that smoothens the transition between reliable and unreliable data patches. Our approach allows for a more nuanced use of all available data, promoting en-hanced learning from regions previously considered unsuit-able for high-quality reconstruction. Extensive experiments across diverse datasets reveal that our approach attains significant gains in efficiency and accuracy, delivering ren-dering speeds of 3 FPS, 7 mins to train a 360° scene, and a 5% improvement in PSNR over existing few-shot methods.
format text
author XU, Yingjie
LIU, Bangzhen
TANG, Hao
DENG, Bailin
HE, Shengfeng
author_facet XU, Yingjie
LIU, Bangzhen
TANG, Hao
DENG, Bailin
HE, Shengfeng
author_sort XU, Yingjie
title Learning with unreliability : Fast few-shot voxel radiance fields with relative geometric consistency
title_short Learning with unreliability : Fast few-shot voxel radiance fields with relative geometric consistency
title_full Learning with unreliability : Fast few-shot voxel radiance fields with relative geometric consistency
title_fullStr Learning with unreliability : Fast few-shot voxel radiance fields with relative geometric consistency
title_full_unstemmed Learning with unreliability : Fast few-shot voxel radiance fields with relative geometric consistency
title_sort learning with unreliability : fast few-shot voxel radiance fields with relative geometric consistency
publisher Institutional Knowledge at Singapore Management University
publishDate 2024
url https://ink.library.smu.edu.sg/sis_research/9775
https://ink.library.smu.edu.sg/context/sis_research/article/10775/viewcontent/2403.17638v1.pdf
_version_ 1819113135185854464