AI Paper Atlas

Research map / 3D vision / Depth and stereo

Revisiting Light Field Rendering with Deep Anti-Aliasing Neural Network

Gaochang Wu, Yebin Liu, Lu Fang, Tianyou Chai

TPAMI 2021 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 68 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 shearing (ablation)DA2N · ICME DSLF (avg)PSNR: 41.41 -> 42.87Improved
add Laplacian downscaling (ablation)DA2N · ICME DSLF (avg)PSNR: 41.33 -> 42.87Improved
add prefilter layers (ablation)DA2N · ICME DSLF (avg)PSNR: 42.55 -> 42.87Improved
add fine-tuning on pseudo EPIs from unstructured LFs (ablation)DA2N · ICME DSLF (avg)PSNR: 40.33 -> 42.87Improved
add fine-tuning on pseudo EPIs (ablation)DA2N · ICME DSLF DD1 x16PSNR: 41.21 -> 46.19Improved
add fine-tuning on pseudo EPIs (gap grows with rate) (ablation)DA2N · ICME DSLFPSNR: 1.07dB -> 3.96dBImproved
add shearing on DD3 x16 (ablation)DA2N · ICME DSLF DD3 (14px) x16PSNR: 36.68 -> 37.99Improved

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