AI Paper Atlas

Research map / 3D vision / Depth and stereo

Light Field Reconstruction Using Convolutional Network on EPI and Extended Applications

Gaochang Wu, Yebin Liu, Lu Fang, Qionghai Dai, Tianyou Chai

TPAMI 2018 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 166 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add blur and deblur steps around the CNN (ablation)Our CNN · Real-world 30 scenesPSNR: 37.15 -> 41.02Improved
add blur and deblur steps around the CNN (ablation)Our CNN · Stanford Lytro Reflective 29PSNR: 44.84 -> 46.10Improved
add blur and deblur steps around the CNN (ablation)Our CNN · Stanford Lytro Occlusion 16PSNR: 35.89 -> 38.86Improved
add learned CNN restoration to blur-bicubic-deblur (ablation)blur-deblur framework · Real-world 30 scenesPSNR: 34.97 -> 41.02Improved
add learned restoration instead of bicubic (ablation)blur-deblur framework · HCI Buddha 3x3PSNR: 34.71 -> 43.20Improved
add learned restoration instead of bicubic (ablation)blur-deblur framework · HCI Buddha 5x5PSNR: 39.23 -> 46.42Improved
add learned restoration instead of bicubic (ablation)blur-deblur framework · HCI Mona 3x3PSNR: 38.21 -> 44.37Improved
add learned restoration instead of bicubic (ablation)blur-deblur framework · HCI Mona 5x5PSNR: 42.66 -> 51.07Improved
use our residual network instead of FSRCNN as restoration step (ablation)blur-deblur framework · HCI Mona 5x5PSNR: 49.75 -> 51.07Improved
use our residual network instead of FSRCNN as restoration step (ablation)blur-deblur framework · HCI Buddha 3x3PSNR: 42.60 -> 43.20Improved
use Gaussian blur kernel instead of sinc kernel (ablation)EPI blur step · Stanford Light Field ArchiveMSE between blurred and upsampled EPIs and blurred ground truth: 0.153 -> 0.061Improved
use Gaussian blur kernel instead of Butterworth kernel (ablation)EPI blur step · Stanford Light Field ArchiveMSE between blurred and upsampled EPIs and blurred ground truth: 0.089 -> 0.061Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy