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

Xu, Yingjie, Liu, Bangzhen, Tang, Hao, Deng, Bailin ORCID: https://orcid.org/0000-0002-0158-7670 and He, Shengfeng 2024. Learning with unreliability: Fast few-shot Voxel radiance fields with relative geometric consistency. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, Seattle, 17 June - 21 June 2024.

Preview	PDF - Supplemental Material Download (1MB) | Preview
	PDF - Accepted Post-Print Version Download (4MB)

Abstract

We propose a voxel-based optimization framework, ReVoRF, for few-shot radiance fields that strategically address 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 absolute 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 synthesized 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 enhanced learning from regions previously considered unsuitable for high-quality reconstruction. Extensive experiments across diverse datasets reveal that our approach attains significant gains in efficiency and accuracy, delivering rendering speeds of 3 FPS, 7 mins to train a 360∘ scene, and a 5% improvement in PSNR over existing few-shot methods. Code is available at https://github.com/HKCLynn/ReVoRF.

Item Type:	Conference or Workshop Item (Paper)
Status:	In Press
Schools:	Computer Science & Informatics
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software
Date of First Compliant Deposit:	4 April 2024
Date of Acceptance:	26 February 2024
Last Modified:	09 May 2024 18:56
URI:	https://orca.cardiff.ac.uk/id/eprint/167712

Actions (repository staff only)

Edit Item