AI Paper Atlas

Research map / Image generation / Image restoration

UCMNet: Uncertainty-Aware Context Memory Network for Under-Display Camera Image Restoration

Daehyun Kim, Youngmin Kim, Yoon Ju Oh, Tae Hyun Kim

CVPR 2026 · Image generation › Image restoration · approach: Real-world restoration with unaligned data · 0 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 uncertainty-driven loss (UDL) (ablation)UCMNet with PSNR loss · POLED testPSNR: 33.38 -> 33.59Improved
replace UDL with high-frequency UDL (ablation)UCMNet · POLED testPSNR: 33.59 -> 33.81Improved
add hv-attention in UPT (ablation)UCMNet UPT · POLED testPSNR: 33.59 -> 33.64Improved
add Memory Bank cross-attention (ablation)UCMNet with hv-attention · POLED testPSNR: 33.64 -> 33.69No clear effect
use Context Bank for cross-attention (ablation)UCMNet with hv-attention · POLED testPSNR: 33.64 -> 33.81Improved
use uncertainty feature instead of router with no prior (ablation)UCMNet context generation · POLED testPSNR: 33.48 -> 33.81Improved
use uncertainty feature instead of input feature for retrieval (ablation)UCMNet context generation · POLED testPSNR: 33.63 -> 33.81Improved
bank size 512 instead of 256 (ablation)UCMNet · POLED testPSNR: 33.78 -> 33.60Hurt
bank size 256 instead of 128 (ablation)UCMNet · POLED testPSNR: 33.71 -> 33.78Improved
UCMNet vs BNUDCUCMNet · POLED testPSNR: 33.39 -> 33.81Improved
UCMNet vs FSIUCMNet · SYNTHPSNR: 45.69 -> 46.71Improved
UCMNet vs DarkIR on low-light enhancementUCMNet · LOLv2-RealPSNR: 23.87 -> 23.10Hurt

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