Light Field Reconstruction Based on Compressed Sensing via Deep Learning

Wei, Linhui; Liu, Yu; Wang, Yumei

doi:10.1109/vcip47243.2019.8965747

Cited by 1 publication

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this subsection, we compare the proposed method TCSEPI with other CS methods, i.e., DCT [20], DWT [20], BCS [33], ISAT-Net [34], BCS_4, and TCS [36]. Besides, they are the patch by patch reconstruction methods.…”

Section: B the Effectiveness Of The Proposed Methodsmentioning

confidence: 99%

“…3) BCS_4 is the BCS method with 4D tensor input, which is used to evaluate the effectiveness of tensor-based input images. 4) TCS [36] is our previous work. To evaluate the performance of each algorithm, we test the average PSNR and SSIM when the compression ratio ranges from 0.05 to 0.3, and the results are shown in Table 2.…”

Section: B the Effectiveness Of The Proposed Methodsmentioning

confidence: 99%

“…Motivated by the CNN-based reconstruction method and based on our prior work [36], we propose a method to realize tensor-based CS and EPI based reconstruction, named TCSEPI. TCSEPI contains two cascaded networks which can solve the compression and reconstruction problem of LF images, respectively.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Tensor-Based Light Field Compressed Sensing and Epipolar Plane Images Reconstruction via Deep Learning

2020

Self Cite

View full text Add to dashboard Cite

Light field (LF) can capture the spatial and angular information of the light in one single exposure. And the LF images are widely used in various fields, especially in immersive media. The rich imaging information in the LF poses great challenges for transmission. However, LF images are sparse and redundant to some extent, which makes LF compression possible. Besides, the compressed sensing (CS) theory shows that images can be recovered from a small number of measurements when they are sparse. In this paper, we propose a Tensor-based Compressed Sensing method to compress images and Epipolar Plane Images for reconstruction (TCSEPI). This method divides the viewpoints of LF images into several regions and stacks the images in each region into a 4D tensor, which conduct CS together and yields measurements with common characteristics. Subsequently, the epipolar plane images are used to reconstruct the LF images and restore the geometric consistency information. To achieve better reconstruction results, we design two cascaded convolutional neural networks to implement the measurement matrix optimization and LF images reconstruction sequentially. Experimental results show the superior performance of TCSEPI, which achieves at least 3dB gain in PSNR and outperforms state-of-the-art in the reconstruction quality. INDEX TERMS Light field, compressed sensing, epipolar plane images, convolutional neural network, image reconstruction

show abstract

Section: B the Effectiveness Of The Proposed Methodsmentioning

confidence: 99%

Section: B the Effectiveness Of The Proposed Methodsmentioning

confidence: 99%