Light Field Reconstruction via Deep Adaptive Fusion of Hybrid Lenses

• URL: http://arxiv.org/abs/2102.07085v3
• Date: Sun, 18 Jun 2023 03:48:01 GMT
• Title: Light Field Reconstruction via Deep Adaptive Fusion of Hybrid Lenses
• Authors: Jing Jin and Mantang Guo and Junhui Hou and Hui Liu and Hongkai Xiong
• Abstract summary: This paper explores the problem of reconstructing high-resolution light field (LF) images from hybrid lenses. We propose a novel end-to-end learning-based approach, which can comprehensively utilize the specific characteristics of the input. Our framework could potentially decrease the cost of high-resolution LF data acquisition and benefit LF data storage and transmission.
• Score: 67.01164492518481
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This paper explores the problem of reconstructing high-resolution light field (LF) images from hybrid lenses, including a high-resolution camera surrounded by multiple low-resolution cameras. The performance of existing methods is still limited, as they produce either blurry results on plain textured areas or distortions around depth discontinuous boundaries. To tackle this challenge, we propose a novel end-to-end learning-based approach, which can comprehensively utilize the specific characteristics of the input from two complementary and parallel perspectives. Specifically, one module regresses a spatially consistent intermediate estimation by learning a deep multidimensional and cross-domain feature representation, while the other module warps another intermediate estimation, which maintains the high-frequency textures, by propagating the information of the high-resolution view. We finally leverage the advantages of the two intermediate estimations adaptively via the learned attention maps, leading to the final high-resolution LF image with satisfactory results on both plain textured areas and depth discontinuous boundaries. Besides, to promote the effectiveness of our method trained with simulated hybrid data on real hybrid data captured by a hybrid LF imaging system, we carefully design the network architecture and the training strategy. Extensive experiments on both real and simulated hybrid data demonstrate the significant superiority of our approach over state-of-the-art ones. To the best of our knowledge, this is the first end-to-end deep learning method for LF reconstruction from a real hybrid input. We believe our framework could potentially decrease the cost of high-resolution LF data acquisition and benefit LF data storage and transmission.

Related papers

• Hybrid-Supervised Dual-Search: Leveraging Automatic Learning for Loss-free Multi-Exposure Image Fusion [60.221404321514086]
  Multi-exposure image fusion (MEF) has emerged as a prominent solution to address the limitations of digital imaging in representing varied exposure levels. This paper presents a Hybrid-Supervised Dual-Search approach for MEF, dubbed HSDS-MEF, which introduces a bi-level optimization search scheme for automatic design of both network structures and loss functions.
  arXiv  Detail & Related papers  (2023-09-03T08:07:26Z)
• Enhancing Low-light Light Field Images with A Deep Compensation Unfolding Network [52.77569396659629]
  This paper presents the deep compensation network unfolding (DCUNet) for restoring light field (LF) images captured under low-light conditions. The framework uses the intermediate enhanced result to estimate the illumination map, which is then employed in the unfolding process to produce a new enhanced result. To properly leverage the unique characteristics of LF images, this paper proposes a pseudo-explicit feature interaction module.
  arXiv  Detail & Related papers  (2023-08-10T07:53:06Z)
• Dual-Camera Super-Resolution with Aligned Attention Modules [56.54073689003269]
  We present a novel approach to reference-based super-resolution (RefSR) with the focus on dual-camera super-resolution (DCSR) Our proposed method generalizes the standard patch-based feature matching with spatial alignment operations. To bridge the domain gaps between real-world images and the training images, we propose a self-supervised domain adaptation strategy.
  arXiv  Detail & Related papers  (2021-09-03T07:17:31Z)
• Scale-Consistent Fusion: from Heterogeneous Local Sampling to Global Immersive Rendering [9.893045525907219]
  Image-based geometric modeling and novel view synthesis based on sparse, large-baseline samplings are challenging but important tasks for emerging multimedia applications such as virtual reality and immersive telepresence. With the popularization of commercial light field (LF) cameras, capturing LF images (LFIs) is as convenient as taking regular photos, and geometry information can be reliably inferred. We propose a novel scale-consistent volume rescaling algorithm that robustly aligns the disparity probability volumes (DPV) among different captures for scale-consistent global geometry fusion.
  arXiv  Detail & Related papers  (2021-06-17T14:27:08Z)
• Deep Selective Combinatorial Embedding and Consistency Regularization for Light Field Super-resolution [93.95828097088608]
  Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution. The high-dimensionality characteristic and complex geometrical structure of LF images make the problem more challenging than traditional single-image SR. We propose a novel learning-based LF spatial SR framework to explore the coherence among LF sub-aperture images. Experimental results over both synthetic and real-world LF datasets demonstrate the significant advantage of our approach over state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-09-26T08:34:37Z)
• Light Field Spatial Super-resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization [99.96632216070718]
  Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution. The high-dimensional spatiality characteristic and complex geometrical structure of LF images make the problem more challenging than traditional single-image SR. We propose a novel learning-based LF framework, in which each view of an LF image is first individually super-resolved.
  arXiv  Detail & Related papers  (2020-04-05T14:39:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.