arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.09236cs.CVeess.IV
收藏

用于光谱恢复的一次性神经波段选择

One-shot neural band selection for spectral recovery

Beihang University(北京航空航天大学);Hangzhou Innovation Institute, Beihang University(北京航空航天大学杭州创新研究院);School of Software, Beihang University(北京航空航天大学软件学院);ShiFang Technology Inc.(十方科技公司);State Key Laboratory of Virtual Reality Technology and Systems, Beihang University(北京航空航天大学虚拟现实技术与系统国家重点实验室)

Hai-Miao Hu, Zhenbo Xu, Wenshuai Xu, You Song, YiTao Zhang, Liu Liu, Zhilin Han, Ajin Meng

AI总结:

提出一种用于光谱恢复的一次性神经波段选择(NBS)框架,基于连续松弛和梯度下降实现高效波段搜索,利用波段相关性矩阵逐步抑制相似相邻波段,在NTIRE 2022挑战赛中取得一致性能提升。

摘要:

波段选择对光谱恢复质量有很大影响。为解决这一不适定逆问题,大多数波段选择方法采用手工设计的先验,或利用聚类或稀疏正则化约束来寻找最显著的波段。由于针对不同选择频率或不同波段组合进行重复训练的计算成本,这些方法要么非常缓慢。许多传统方法依赖场景先验,因此不适用于其他场景。本文提出了一种用于光谱恢复的新型一次性神经波段选择(NBS)框架。与具有离散搜索空间和不可微搜索策略的传统搜索方法不同,我们的NBS基于波段选择过程的连续松弛,从而允许使用梯度下降进行高效的波段搜索。为实现一次性选择任意数量波段的兼容性,我们进一步利用波段相关性矩阵来逐步抑制相似的相邻波段。在NTIRE 2022光谱重建挑战赛上的广泛评估表明,当使用四种不同的光谱恢复方法进行检验时,我们的NBS相对于竞争基线取得了一致的性能提升。我们的代码将公开提供。

英文摘要:

Band selection has a great impact on the spectral recovery quality. To solve this ill-posed inverse problem, most band selection methods adopt hand-crafted priors or exploit clustering or sparse regularization constraints to find most prominent bands. These methods are either very slow due to the computational cost of repeatedly training with respect to different selection frequencies or different band combinations. Many traditional methods rely on the scene prior and thus are not applicable to other scenarios. In this paper, we present a novel one-shot Neural Band Selection (NBS) framework for spectral recovery. Unlike conventional searching approaches with a discrete search space and a non-differentiable search strategy, our NBS is based on the continuous relaxation of the band selection process, thus allowing efficient band search using gradient descent. To enable the compatibility for se- lecting any number of bands in one-shot, we further exploit the band-wise correlation matrices to progressively suppress similar adjacent bands. Extensive evaluations on the NTIRE 2022 Spectral Reconstruction Challenge demonstrate that our NBS achieves consistent performance gains over competitive baselines when examined with four different spectral recov- ery methods. Our code will be publicly available.

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。

↑