NVS-SQA: Exploring Self-Supervised Quality Representation Learning for Neurally Synthesized Scenes without References

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Qu, Qiang, Shen, Yiran, Chen, Xiaoming, Chung, Yuk Ying, Cai, Weidong, Liu, Tongliang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908610486861824
author Qu, Qiang
Shen, Yiran
Chen, Xiaoming
Chung, Yuk Ying
Cai, Weidong
Liu, Tongliang
author_facet Qu, Qiang
Shen, Yiran
Chen, Xiaoming
Chung, Yuk Ying
Cai, Weidong
Liu, Tongliang
contents Neural View Synthesis (NVS), such as NeRF and 3D Gaussian Splatting, effectively creates photorealistic scenes from sparse viewpoints, typically evaluated by quality assessment methods like PSNR, SSIM, and LPIPS. However, these full-reference methods, which compare synthesized views to reference views, may not fully capture the perceptual quality of neurally synthesized scenes (NSS), particularly due to the limited availability of dense reference views. Furthermore, the challenges in acquiring human perceptual labels hinder the creation of extensive labeled datasets, risking model overfitting and reduced generalizability. To address these issues, we propose NVS-SQA, a NSS quality assessment method to learn no-reference quality representations through self-supervision without reliance on human labels. Traditional self-supervised learning predominantly relies on the "same instance, similar representation" assumption and extensive datasets. However, given that these conditions do not apply in NSS quality assessment, we employ heuristic cues and quality scores as learning objectives, along with a specialized contrastive pair preparation process to improve the effectiveness and efficiency of learning. The results show that NVS-SQA outperforms 17 no-reference methods by a large margin (i.e., on average 109.5% in SRCC, 98.6% in PLCC, and 91.5% in KRCC over the second best) and even exceeds 16 full-reference methods across all evaluation metrics (i.e., 22.9% in SRCC, 19.1% in PLCC, and 18.6% in KRCC over the second best).
format Preprint
id arxiv_https___arxiv_org_abs_2501_06488
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NVS-SQA: Exploring Self-Supervised Quality Representation Learning for Neurally Synthesized Scenes without References
Qu, Qiang
Shen, Yiran
Chen, Xiaoming
Chung, Yuk Ying
Cai, Weidong
Liu, Tongliang
Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
Multimedia
Image and Video Processing
Neural View Synthesis (NVS), such as NeRF and 3D Gaussian Splatting, effectively creates photorealistic scenes from sparse viewpoints, typically evaluated by quality assessment methods like PSNR, SSIM, and LPIPS. However, these full-reference methods, which compare synthesized views to reference views, may not fully capture the perceptual quality of neurally synthesized scenes (NSS), particularly due to the limited availability of dense reference views. Furthermore, the challenges in acquiring human perceptual labels hinder the creation of extensive labeled datasets, risking model overfitting and reduced generalizability. To address these issues, we propose NVS-SQA, a NSS quality assessment method to learn no-reference quality representations through self-supervision without reliance on human labels. Traditional self-supervised learning predominantly relies on the "same instance, similar representation" assumption and extensive datasets. However, given that these conditions do not apply in NSS quality assessment, we employ heuristic cues and quality scores as learning objectives, along with a specialized contrastive pair preparation process to improve the effectiveness and efficiency of learning. The results show that NVS-SQA outperforms 17 no-reference methods by a large margin (i.e., on average 109.5% in SRCC, 98.6% in PLCC, and 91.5% in KRCC over the second best) and even exceeds 16 full-reference methods across all evaluation metrics (i.e., 22.9% in SRCC, 19.1% in PLCC, and 18.6% in KRCC over the second best).
title NVS-SQA: Exploring Self-Supervised Quality Representation Learning for Neurally Synthesized Scenes without References
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
Multimedia
Image and Video Processing
url https://arxiv.org/abs/2501.06488