High-performance reconstruction method combining total variation with a video denoiser for compressed ultrafast imaging
Compressed ultrafast photography (CUP) is a novel two-dimensional (2D) imaging technique to capture ultrafast dynamic scenes. Effective image reconstruction is essential in CUP systems. However, existing reconstruction algorithms mostly rely on image priors and complex parameter spaces. Therefore, in general, they are time-consuming and result in poor imaging quality, which limits their practical applications. In this paper, we propose a novel reconstruction algorithm, to the best of our knowledge, named plug-in-plug-fast deep video denoising net-total variation (PnP-TV-FastDVDnet), which exploits an image's spatial features and correlation features in the temporal dimension. Therefore, it offers higher-quality images than those in previously reported methods. First, we built a forward mathematical model of the CUP, and the closed-form solution of the three suboptimization problems was derived according to plug-in and plug-out frames. Secondly, we used an advanced video denoising algorithm based on a neural network named FastDVDnet to solve the denoising problem. The peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) are improved on actual CUP data compared with traditional algorithms. On benchmark and real CUP datasets, the proposed method shows the comparable visual results while reducing the running time by 96% over state-of-the-art algorithms.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:63 |
---|---|
Enthalten in: |
Applied optics - 63(2024), 8 vom: 10. März, Seite C32-C40 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Pei, Chengquan [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Revised 03.04.2024 published: Print Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.1364/AO.506058 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM370580540 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM370580540 | ||
003 | DE-627 | ||
005 | 20240404000922.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240404s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1364/AO.506058 |2 doi | |
028 | 5 | 2 | |a pubmed24n1363.xml |
035 | |a (DE-627)NLM370580540 | ||
035 | |a (NLM)38568625 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Pei, Chengquan |e verfasserin |4 aut | |
245 | 1 | 0 | |a High-performance reconstruction method combining total variation with a video denoiser for compressed ultrafast imaging |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 03.04.2024 | ||
500 | |a published: Print | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a Compressed ultrafast photography (CUP) is a novel two-dimensional (2D) imaging technique to capture ultrafast dynamic scenes. Effective image reconstruction is essential in CUP systems. However, existing reconstruction algorithms mostly rely on image priors and complex parameter spaces. Therefore, in general, they are time-consuming and result in poor imaging quality, which limits their practical applications. In this paper, we propose a novel reconstruction algorithm, to the best of our knowledge, named plug-in-plug-fast deep video denoising net-total variation (PnP-TV-FastDVDnet), which exploits an image's spatial features and correlation features in the temporal dimension. Therefore, it offers higher-quality images than those in previously reported methods. First, we built a forward mathematical model of the CUP, and the closed-form solution of the three suboptimization problems was derived according to plug-in and plug-out frames. Secondly, we used an advanced video denoising algorithm based on a neural network named FastDVDnet to solve the denoising problem. The peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) are improved on actual CUP data compared with traditional algorithms. On benchmark and real CUP datasets, the proposed method shows the comparable visual results while reducing the running time by 96% over state-of-the-art algorithms | ||
650 | 4 | |a Journal Article | |
700 | 1 | |a Li, David Day-Uei |e verfasserin |4 aut | |
700 | 1 | |a Shen, Qian |e verfasserin |4 aut | |
700 | 1 | |a Zhang, Shian |e verfasserin |4 aut | |
700 | 1 | |a Qi, Dalong |e verfasserin |4 aut | |
700 | 1 | |a Jin, Chengzhi |e verfasserin |4 aut | |
700 | 1 | |a Dong, Le |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Applied optics |d 1966 |g 63(2024), 8 vom: 10. März, Seite C32-C40 |w (DE-627)NLM114401330 |x 1539-4522 |7 nnns |
773 | 1 | 8 | |g volume:63 |g year:2024 |g number:8 |g day:10 |g month:03 |g pages:C32-C40 |
856 | 4 | 0 | |u http://dx.doi.org/10.1364/AO.506058 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 63 |j 2024 |e 8 |b 10 |c 03 |h C32-C40 |