Results 1 to 10 of about 24,825,488 (305)
Learning-based view synthesis for light field cameras [PDF]
ACM Transactions on Graphics, 2016 With the introduction of consumer light field cameras, light field imaging has recently become widespread. However, there is an inherent trade-off between the angular and spatial resolution, and thus, these cameras often sparsely sample in either spatial
N. Kalantari +2 more
semanticscholar +3 more sources
Light Field Image Processing: An Overview
IEEE Journal on Selected Topics in Signal Processing, 2017 Light field imaging has emerged as a technology allowing to capture richer visual information from our world. As opposed to traditional photography, which captures a 2D projection of the light in the scene integrating the angular domain, light fields ...
Gaochang Wu +7 more
semanticscholar +3 more sources
Fourier light-field microscopy.
Optics Express, 2019 Observing the various anatomical and functional information that spans many spatiotemporal scales with high resolution provides deep understandings of the fundamentals of biological systems. Light-field microscopy (LFM) has recently emerged as a scanning-
Changliang Guo +4 more
semanticscholar +3 more sources
Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering [PDF]
Neural Information Processing Systems, 2021 Inferring representations of 3D scenes from 2D observations is a fundamental problem of computer graphics, computer vision, and artificial intelligence.
Vincent Sitzmann +4 more
semanticscholar +1 more source
NeILF: Neural Incident Light Field for Physically-based Material Estimation [PDF]
European Conference on Computer Vision, 2022 We present a differentiable rendering framework for material and lighting estimation from multi-view images and a reconstructed geometry. In the framework, we represent scene lightings as the Neural Incident Light Field (NeILF) and material properties as
Yao Yao +7 more
semanticscholar +1 more source
Light Field Image Super-Resolution With Transformers [PDF]
IEEE Signal Processing Letters, 2021 Light field (LF) image super-resolution (SR) aims at reconstructing high-resolution LF images from their low-resolution counterparts. Although CNN-based methods have achieved remarkable performance in LF image SR, these methods cannot fully model the non-
Zhengyu Liang +4 more
semanticscholar +1 more source
Detail-Preserving Transformer for Light Field Image Super-Resolution [PDF]
AAAI Conference on Artificial Intelligence, 2022 Recently, numerous algorithms have been developed to tackle the problem of light field super-resolution (LFSR), i.e., super-resolving low-resolution light fields to gain high-resolution views.
Shun-Zhou Wang +3 more
semanticscholar +1 more source
Single multimode fibre for in vivo light-field-encoded endoscopic imaging [PDF]
Nature Photonics, 2022 Spatial-frequency tracking adaptive beacon light-field encoded endoscopy enables imaging through a single multimode fibre under bending and twisting. In vivo imaging with subcellular resolution is demonstrated in mice models.
Zhong Wen +12 more
semanticscholar +1 more source
Learning to Deblur using Light Field Generated and Real Defocus Images [PDF]
Computer Vision and Pattern Recognition, 2022 Defocus deblurring is a challenging task due to the spatially varying nature of defocus blur. While deep learning approach shows great promise in solving image restoration problems, defocus deblurring demands accurate training data that consists of all ...
Lingyan Ruan +3 more
semanticscholar +1 more source
Light Field Neural Rendering [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021 Classical light field rendering for novel view synthesis can accurately reproduce view-dependent effects such as reflection, refraction, and translucency, but requires a dense view sampling of the scene.
Mohammed Suhail +3 more
semanticscholar +1 more source