AI Paper Atlas

Research map / 3D vision / Depth and stereo

End-to-end View Synthesis for Light Field Imaging with Pseudo 4DCNN

Yunlong Wang, Fei Liu, Zilei Wang, Guangqi Hou, Zhenan Sun, Tieniu Tan

ECCV 2018 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 148 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 prior sensitive loss (ablation)Pseudo 4DCNN · 30 ScenesPSNR (dB): 42.34 -> 43.28Improved
use a separately trained row and column network instead of the same sub-network (Fr=Fc) (ablation)Pseudo 4DCNN · 30 ScenesPSNR (dB): 42.90 -> 43.28Improved
add 2D learnable interpolation (ablation)Pseudo 4DCNN · 30 ScenesPSNR (dB): 40.15 -> 43.28Improved
add 3D detail-restoration CNN (ablation)Pseudo 4DCNN · 30 ScenesPSNR (dB): 39.01 -> 43.28Improved
add prior sensitive loss (ablation)Pseudo 4DCNN · 30 ScenesSSIM: 0.9901 -> 0.9916Improved
add 3D detail-restoration CNN (ablation)Pseudo 4DCNN · 30 ScenesSSIM: 0.9876 -> 0.9916Improved
replace Wu et al. EPI blur-restoration-deblur with Pseudo 4DCNNWu et al. · 30 ScenesPSNR (dB): 40.83 -> 43.28Improved
replace Kalantari et al. disparity-based synthesis with Pseudo 4DCNNKalantari et al. · 30 ScenesPSNR (dB): 37.43 -> 43.28Improved
replace Wu et al. with Pseudo 4DCNNWu et al. · 30 Scenestime per synthesized view (sec): 3.38 -> 0.28Improved
replace Kalantari et al. with Pseudo 4DCNNKalantari et al. · 30 Scenestime per synthesized view (sec): 8.59 -> 0.28Improved
replace Wu et al. with Pseudo 4DCNN on non-Lambertian synthetic scenesWu et al. · KitchenPSNR (dB): 35.57 -> 38.12Improved
replace Wu et al. with Pseudo 4DCNN on iris light fieldsWu et al. · IrisPSNR (dB): 34.98 -> 40.14Improved

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