Computational reconstruction plays a vital role in computer vision and computational photography. Most of the conventional optimization and deep learning techniques explore local information for reconstruction. Recently, nonlocal low-rank (NLR) reconstruction has achieved remarkable success in improving accuracy and generalization. However, the computational cost has inhibited NLR from seeking global structural similarity, which consequentially keeps it trapped in the tradeoff between accuracy and efficiency and prevents it from high-dimensional large-scale tasks. To address this challenge, we report here the global low-rank (GLR) optimization technique, realizing highly-efficient large-scale reconstruction with global self-similarity. Inspired by the self-attention mechanism in deep learning, GLR extracts exemplar image patches by feature detection instead of conventional uniform selection. This directly produces key patches using structural features to avoid burdensome computational redundancy. Further, it performs patch matching across the entire image via neural-based convolution, which produces the global similarity heat map in parallel, rather than conventional sequential block-wise matching. As such, GLR improves patch grouping efficiency by more than one order of magnitude. We experimentally demonstrate GLR's effectiveness on temporal, frequency, and spectral dimensions, including different computational imaging modalities of compressive temporal imaging, magnetic resonance imaging, and multispectral filter array demosaicing. This work presents the superiority of inherent fusion of deep learning strategies and iterative optimization, and breaks the persistent dilemma of the tradeoff between accuracy and efficiency for various large-scale reconstruction tasks.
翻译:计算成本抑制了NLR寻求全球结构相似性,从而使得它无法在准确性和效率之间进行权衡,无法完成高尺度的大规模任务。为了应对这一挑战,我们在此报告全球低级优化技术(GLR)优化技术(GLR)优化技术(GLR)优化技术(GLR)优化技术(GLR)优化技术(GLR)优化技术(GLR)优化技术(GLR)优化技术(GLR)优化技术(GLR)优化技术(GLR)优化技术(GLR)的优化大规模重建技术(GLR)为重建而探索当地信息。最近,非本地低级(NLR)重建技术(NLR)在提高准确性准确性(NLR)的改进方面取得了显著成功。 计算成本成本计算成本计算(GLRR)(GLRR)利用结构特征直接产生关键的补丁,以避免繁琐的计算冗误。此外,它通过基于神经的混变动(NLR)的连动,产生全球相似性热热热热图,而不是常规的连续相系相配对齐(GLRLRLRLRLRLRLR)的比(BAR)战略(BAR)的大幅)的精确度(BLR)和(BAR)的深度(BLVLR)的升级(BAR)的升级(BAR)的深度)的升级(BAR)的升级(BAR)(BL)(BLV)(BL)(BAR)(BAR)(BLV)(BR)(BR)(B)(B)(B)(B)(B)(B)(B)(B)(L)(B)(B)(B)(B)(B)(B)(B)(B)(B)(B)(B)(B)(BL)(B)(B)(B)(B)(B)(B)(B)(B)(BL)(B)(B)(B)(B)(B)(B)(B)(B)(B)(B)(B)(B)(B)(B)(B)