AI Paper Atlas

Research map / Image generation / Image restoration

Building Bridge Across the Time: Disruption and Restoration of Murals In the Wild

Huiyang Shao, Qianqian Xu, Peisong Wen, Peifeng Gao, Zhiyong Yang, Qingming Huang

ICCV 2023 · Image generation › Image restoration · approach: Efficient restoration architectures · 19 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
train baselines on the proposed physically simulated mural dataset instead of the previous masked dataset (ablation)baseline restorers · real damaged muralsPSNR/FID: SwinIR PSNR 13.51 -> 17.83; ADF FID 57.13 -> 47.59Improved
add the damage attention map (DAM) module to the guided-diffusion backbone (ablation)ADF · mural benchmarkPSNR/SSIM/IS/FIDImproved
combine heatmap loss Lh with DAM (ablation)ADF · mural benchmarkFIDImproved
add edge loss Ls (ablation)ADF · mural benchmarkedge sharpness (qualitative)Improved
add estimation loss Le (ablation)ADF · mural benchmarkperformance and generation speedImproved
transplant DAM and losses to a conditional GAN backbone (ablation)conditional GAN · mural restoration (qualitative)restoration qualityImproved
use ADF instead of strongest baselines on benchmarkmural restoration · mural benchmarkFID: 37.23 -> 35.88Improved
vary degradation: higher cracking and peeling in training data (ablation)mural simulation dataset · mural restorationrepainting abilityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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