NeRF-NQA: No-Reference Quality Assessment for Scenes Generated by NeRF and Neural View Synthesis Methods

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Qu, Qiang, Liang, Hanxue, Chen, Xiaoming, Chung, Yuk Ying, Shen, Yiran
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910739400228864
author Qu, Qiang
Liang, Hanxue
Chen, Xiaoming
Chung, Yuk Ying
Shen, Yiran
author_facet Qu, Qiang
Liang, Hanxue
Chen, Xiaoming
Chung, Yuk Ying
Shen, Yiran
contents Neural View Synthesis (NVS) has demonstrated efficacy in generating high-fidelity dense viewpoint videos using a image set with sparse views. However, existing quality assessment methods like PSNR, SSIM, and LPIPS are not tailored for the scenes with dense viewpoints synthesized by NVS and NeRF variants, thus, they often fall short in capturing the perceptual quality, including spatial and angular aspects of NVS-synthesized scenes. Furthermore, the lack of dense ground truth views makes the full reference quality assessment on NVS-synthesized scenes challenging. For instance, datasets such as LLFF provide only sparse images, insufficient for complete full-reference assessments. To address the issues above, we propose NeRF-NQA, the first no-reference quality assessment method for densely-observed scenes synthesized from the NVS and NeRF variants. NeRF-NQA employs a joint quality assessment strategy, integrating both viewwise and pointwise approaches, to evaluate the quality of NVS-generated scenes. The viewwise approach assesses the spatial quality of each individual synthesized view and the overall inter-views consistency, while the pointwise approach focuses on the angular qualities of scene surface points and their compound inter-point quality. Extensive evaluations are conducted to compare NeRF-NQA with 23 mainstream visual quality assessment methods (from fields of image, video, and light-field assessment). The results demonstrate NeRF-NQA outperforms the existing assessment methods significantly and it shows substantial superiority on assessing NVS-synthesized scenes without references. An implementation of this paper are available at https://github.com/VincentQQu/NeRF-NQA.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08029
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle NeRF-NQA: No-Reference Quality Assessment for Scenes Generated by NeRF and Neural View Synthesis Methods
Qu, Qiang
Liang, Hanxue
Chen, Xiaoming
Chung, Yuk Ying
Shen, Yiran
Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
Multimedia
Image and Video Processing
Neural View Synthesis (NVS) has demonstrated efficacy in generating high-fidelity dense viewpoint videos using a image set with sparse views. However, existing quality assessment methods like PSNR, SSIM, and LPIPS are not tailored for the scenes with dense viewpoints synthesized by NVS and NeRF variants, thus, they often fall short in capturing the perceptual quality, including spatial and angular aspects of NVS-synthesized scenes. Furthermore, the lack of dense ground truth views makes the full reference quality assessment on NVS-synthesized scenes challenging. For instance, datasets such as LLFF provide only sparse images, insufficient for complete full-reference assessments. To address the issues above, we propose NeRF-NQA, the first no-reference quality assessment method for densely-observed scenes synthesized from the NVS and NeRF variants. NeRF-NQA employs a joint quality assessment strategy, integrating both viewwise and pointwise approaches, to evaluate the quality of NVS-generated scenes. The viewwise approach assesses the spatial quality of each individual synthesized view and the overall inter-views consistency, while the pointwise approach focuses on the angular qualities of scene surface points and their compound inter-point quality. Extensive evaluations are conducted to compare NeRF-NQA with 23 mainstream visual quality assessment methods (from fields of image, video, and light-field assessment). The results demonstrate NeRF-NQA outperforms the existing assessment methods significantly and it shows substantial superiority on assessing NVS-synthesized scenes without references. An implementation of this paper are available at https://github.com/VincentQQu/NeRF-NQA.
title NeRF-NQA: No-Reference Quality Assessment for Scenes Generated by NeRF and Neural View Synthesis Methods
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
Multimedia
Image and Video Processing
url https://arxiv.org/abs/2412.08029