AI Paper Atlas

Research map / 3D vision / Depth and stereo

Fast Light Field Reconstruction With Deep Coarse-To-Fine Modeling of Spatial-Angular Clues

Henry Wing Fung Yeung, Junhui Hou, Jie Chen, Yuk Ying Chung, Xiaoming Chen

ECCV 2018 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 188 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
use extrapolated input view positions (1 row and column) together with interpolation (ablation)Ours 8L · 2x2-8x8, 222 real-world LFsPSNR: 37.55 -> 39.93Improved
extrapolate 2 rows and columns of input views (ablation)Ours 8L · 2x2-8x8, 222 real-world LFsPSNR: 37.55 -> 40.09Improved
extrapolate 2 instead of 1 row/column of input views (ablation)Ours Extra. 1 · 2x2-8x8, 222 real-world LFsPSNR: 39.93 -> 40.09Improved
use 16 alternating convolutions in synthesis network vs 8 (ablation)Ours · 2x2-8x8, 222 real-world LFsPSNR: 37.55 -> 37.76Improved
use proposed model instead of Kalantari et al.Ours 4L · 3x3-7x7 average over datasetsPSNR: 43.18 -> 44.06Improved
use proposed model instead of Wu et al.Ours 4L · 3x3-7x7 average over datasetsPSNR: 40.75 -> 44.06Improved
use proposed model on microscope Neurons 20xOurs 4L vs Kalantari et al. · Neurons 20xPSNR: 28.45 -> 30.69Improved
use proposed Ours 8L instead of Wu et al.Ours 8L · 3x3-9x9 HCI Buddha and MonaPSNR: 43.79 -> 44.72Improved
use proposed 16L model instead of Kalantari et al.Ours 16L · 2x2-8x8 OcclusionsPSNR: 31.81 -> 32.68Improved
use proposed model instead of Wu et al. on SSIMOurs 4L · 3x3-7x7 averageSSIM: 0.9861 -> 0.9889Improved
use proposed model instead of Wu et al. (HCI, SSIM-based comparison)Ours 8L · 3x3-9x9 HCI Buddha and MonaSSIM: 0.9981 -> 0.9896Hurt

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