AI Paper Atlas

Research map / Image generation / Image restoration

Deep Texture and Structure Aware Filtering Network for Image Smoothing

Kaiyue Lu, Shaodi You, Nick Barnes

ECCV 2018 · Image generation › Image restoration · approach: Dehazing and deraining · 46 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 structure guidance (HED) to the filtering network (ablation)filtering network · Generated texture dataset test (guidance ablation)MSE: 0.0316 -> 0.0215Improved
add texture guidance (TPN) to the filtering network (ablation)filtering network · Generated texture dataset test (guidance ablation)MSE: 0.0316 -> 0.0118Improved
add texture guidance on top of structure guidance (ablation)filtering network · Generated texture dataset test (guidance ablation)MSE: 0.0215 -> 0.0059Improved
add structure guidance on top of texture guidance (ablation)filtering network · Generated texture dataset test (guidance ablation)MSE: 0.0118 -> 0.0059Improved
fine-tune the whole network jointly after separate training (ablation)TSAFN · Generated texture dataset test (guidance ablation)PSNR: 24.78 -> 25.07Improved
add structure guidance to the filtering network (ablation)filtering network · Generated texture dataset test (guidance ablation)PSNR: 20.32 -> 21.71Improved
add texture guidance only (no structure guidance) (ablation)filtering network · Generated texture dataset test (guidance ablation)SSIM: 0.7934 -> 0.8201Mixed
replace hand-crafted filters with TSAFNDGF (best hand-crafted) · Generated texture dataset test (hand-crafted filters)MSE: 0.1247 -> 0.0051Improved
replace best retrained deep filter with TSAFNCEILNet · Generated texture dataset test (deep models retrained)MSE: 0.0156 -> 0.0051Improved
use learned TPN instead of hand-crafted separation for texture extractionSGTD (best separation filter) · Generated texture dataset test (texture extraction)MSE (texture extraction): 0.1315 -> 0.0196Improved
use TPN on a new texture setSGTD · 100 new images (texture extraction)MSE (texture extraction): 0.1608 -> 0.0212Improved

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