LF-BVN：用于自监督光场去噪的盲视角网络
LF-BVN: Blind-View Network for Self-Supervised Light Field Denoising
将盲点去噪原理从单图扩展到光场多视图，利用视角间噪声不相干性构造自监督信号，并引入几何不变性掩码与潜变量体一致性约束，为无干净数据的光场去噪提供了可复用框架。
原文依据 we extend the blind-spot principle to the LF domain and propose a novel LF Blind-View denoising Network (LF-BVN)
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近年来，基于学习的光场（LF）图像去噪方法取得了令人瞩目的成果。然而，这些方法严重依赖大规模噪声-干净图像对，且往往难以泛化到未见过的或复杂的噪声。在本工作中，我们观察到光场图像固有的多视图一致性使得噪声在视角间高度不可能保持相干，这为自监督去噪提供了更可靠的监督信号。基于这一洞察，我们将盲点原理扩展到光场领域，并提出了一种新颖的光场盲视角去噪网络（LF-BVN）。我们首先引入几何不变性掩码，利用角度冗余实现高效的全视角监督。为了强制跨视角光度一致性，我们进一步引入潜变量表征体并强制它们之间的一致性。此外，我们利用焦点堆栈从噪声观测中提取潜变量深度线索，提供进一步的引导。大量实验表明，LF-BVN在无需干净数据或外部监督的情况下，实现了具有竞争力的去噪性能，同时保持了强跨视角一致性。
英文原文摘要 1144 字符
Recent advances in learning-based Light Field (LF) image denoising have achieved impressive results. However, these methods rely heavily on large-scale noisy-clean image pairs and often fail to generalize to unseen or complex noise.In this work, we observe that the inherent multi-view consistency of LF images makes it highly unlikely for noise to be coherent across views, offering a more reliable supervisory signal for self-supervised denoising.Building on this insight, we extend the blind-spot principle to the LF domain and propose a novel LF Blind-View denoising Network (LF-BVN). We first introduce a geometric invariance mask that leverages angular redundancy for efficient full-view supervision. To enforce cross-view photometric consistency, we further introduce latent representation volumes and enforce consistency between them.Additionally, we exploit focus stacks to extract latent depth cues from noisy observations, providing further guidance.Extensive experiments show that LF-BVN achieves competitive denoising performance while maintaining strong cross-view consistency without requiring clean data or external supervision.