Probabilistic-based Feature Embedding of 4-D Light Fields for Compressive Imaging and Denoising

Abstract

The high-dimensional nature of the 4-D light field (LF) poses great challenges in achieving efficient and effective feature embedding, that severely impacts the performance of downstream tasks. To tackle this crucial issue, in contrast to existing methods with empirically-designed architectures, we propose a probabilistic-based feature embedding (PFE), which learns a feature embedding architecture by assembling various low-dimensional convolution patterns in a probability space for fully capturing spatial-angular information. Building upon the proposed PFE, we then leverage the intrinsic linear imaging model of the coded aperture camera to construct a cycle-consistent 4-D LF reconstruction network from coded measurements. Moreover, we incorporate PFE into an iterative optimization framework for 4-D LF denoising. Our extensive experiments demonstrate the significant superiority of our methods on both real-world and synthetic 4-D LF images, both quantitatively and qualitatively, when compared with state-of-the-art methods. The source code will be publicly available at https://github.com/lyuxianqiang/LFCA-CR-NET.

References in corpus (8)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Learning-Based View Synthesis for Light Field Cameras
• Disentangling Light Fields for Super-Resolution and Disparity Estimation
• Light Field Image Super-Resolution Using Deformable Convolution
• Accurate Light Field Depth Estimation with Superpixel Regularization over Partially Occluded Regions
• Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework
• Occlusion-aware Unsupervised Learning of Depth from 4-D Light Fields
• Harnessing Multi-View Perspective of Light Fields for Low-Light Imaging