AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Shift-Net: Image Inpainting via Deep Feature Rearrangement

Zhaoyi Yan, Xiaoming Li, Mu Li, Wangmeng Zuo, Shiguang Shan

ECCV 2018 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 539 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
shift the connection at (L-4)-th layer instead of (L-3)-th (ablation)Shift-Net · 256x256 image inferenceruntime per image: 80 ms -> 40 msMixed
shift the connection at (L-2)-th layer instead of (L-3)-th (ablation)Shift-Net · 256x256 image inferenceruntime per image: 80 ms -> 400 msMixed
add guidance loss (ablation)U-Net and Shift-Net · Paris StreetViewvisual quality (qualitative)Improved
use guidance weight 0.001 or at least 0.1 instead of 0.01 (ablation)Shift-Net · Paris StreetViewvisual quality (qualitative)Hurt
add shift operation to U-Net (with guidance loss) (ablation)U-Net · Paris StreetViewvisual quality (qualitative)Improved
use nearest neighbor search instead of random shift-connection (ablation)Shift-Net · Paris StreetViewvisual quality (qualitative)Improved
vary mask threshold T among 4/16, 5/16, 6/16 (ablation)Shift-Net · Paris StreetViewvisual quality (qualitative)No clear effect
combine CNN with exemplar-based inpainting end-to-end (Shift-Net vs MNPS)Shift-Net · Paris StreetViewPSNR: 25.98 -> 26.51Improved

Later papers that compared with this method

1 later accepted paper reports Shift-Net-18-9 (1.76M) as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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