NeRF-NQA：针对NeRF及神经视图合成方法生成场景的无参考质量评估
NeRF-NQA: No-Reference Quality Assessment for Scenes Generated by NeRF and Neural View Synthesis Methods
AI总结：
针对现有质量评估方法不适配神经视图合成场景、密集真实视角缺失导致全参考评估难的问题，提出首个无参考评估方法NeRF-NQA，通过逐视角+逐点的联合策略评估，性能显著优于23种主流方法。
摘要：
神经视图合成（Neural View Synthesis, NVS）已被证明可利用稀疏视角图像集生成高保真的密集视角视频。然而，PSNR、SSIM、LPIPS等现有质量评估方法并非针对NVS与NeRF变体合成的密集视角场景设计，因此往往无法充分捕捉NVS合成场景的感知质量，包括空间与角度维度的质量表现。此外，密集真实视角的缺失使得对NVS合成场景开展全参考质量评估颇具难度——例如LLFF等数据集仅提供稀疏图像，不足以支撑完整的全参考评估。为解决上述问题，我们提出NeRF-NQA，这是首个针对NVS与NeRF变体合成的密集观测场景的无参考质量评估方法。NeRF-NQA采用联合质量评估策略，整合逐视角与逐点两类方法来评估NVS生成场景的质量：逐视角方法评估单张合成视图的空间质量以及整体的视图间一致性，逐点方法则聚焦于场景表面点的角度质量及其复合点间质量。我们开展了大量评估实验，将NeRF-NQA与23种主流视觉质量评估方法（涵盖图像、视频及光场评估领域）进行对比。结果表明，NeRF-NQA的表现显著优于现有评估方法，在无参考条件下评估NVS合成场景时展现出突出优势。本文的实现代码可在https://github.com/VincentQQu/NeRF-NQA获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
