AI Paper Atlas

Research map / Image generation / Super-resolution

Spatial-Angular Interaction for Light Field Image Super-Resolution

Yingqian Wang, Longguang Wang, Jungang Yang, Wei An, Jingyi Yu, Yulan Guo

ECCV 2020 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 228 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 angular information path (ablation)LF-InterNet · STFlytro 4xSRPSNR: 29.98 -> 31.65Improved
add spatial 3x3 convolution information (ablation)LF-InterNet · STFlytro 4xSRPSNR: 26.57 -> 31.65Improved
decouple spatial and angular features (vs coupled, same size) (ablation)LF-InterNet · STFlytro 4xSRPSNR: 31.11 -> 31.65Improved
decouple spatial and angular features (vs coupled, same FLOPs) (ablation)LF-InterNet · STFlytro 4xSRPSNR: 31.17 -> 31.65Improved
add first spatial-angular interaction group (ablation)LF-InterNet · STFlytro 4xSRPSNR: 29.84 -> 31.44Improved
increase interaction groups from 1 to 4 (ablation)LF-InterNet · STFlytro 4xSRPSNR: 31.44 -> 31.84Improved
use pixel shuffling instead of bilinear upsampling (ablation)LF-InterNet · STFlytro 4xSRPSNR: 30.71 -> 31.84Improved
use pixel shuffling instead of nearest upsampling (ablation)LF-InterNet · STFlytro 4xSRPSNR: 31.65 -> 31.84Improved
increase angular resolution from 3x3 to 9x9 (ablation)LF-InterNet · STFlytro 4xSRPSNR: 31.30 -> 32.07Improved
increase angular resolution from 7x7 to 9x9 (ablation)LF-InterNet · STFlytro 2xSRPSNR: 39.05 -> 39.08No clear effect
double feature depth from 32 to 64LF-InterNet · LF SR 4x average of 6 datasetsPSNR: 31.57 -> 31.95Improved
use LF-InterNet instead of LF-ATOLF-ATO · UCSD unseen 2xSRPSNR: 41.80 -> 42.36Improved

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