AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

UniProcessor: A Text-induced Unified Low-level Image Processor

Huiyu Duan, Xiongkuo Min, Sijing Wu, Wei Shen, Guangtao Zhai

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 15 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
text-induced context control with subject and manipulation prompts vs PromptIRUniProcessor · CBSD68 30 degradations (average)PSNR: 28.35 -> 30.35Improved
add Q-Former subject-aligned image representation to the context control module (ablation)UniProcessor · Rain streak removalPSNR: 28.23 -> 28.67Improved
add image-aware Q-Former on top of text encoder only (ablation)UniProcessor · Rain streak removalPSNR: 27.76 -> 28.67Improved
add context interaction module (CIM) (ablation)UniProcessor · Low-light enhancementPSNR: 23.03 -> 24.23Improved
inject CIM at levels 5+4+3 instead of only level 5 (ablation)UniProcessor · Rain streak removalPSNR: 28.30 -> 28.67Improved
add CIM at shallow levels (ablation)UniProcessor · Rain streak and low-lightperformance and computeMixed
sequential removal of both degradations with text prompts vs PromptIR twiceUniProcessor · Rain + low-lightPSNR: 23.3 -> 28.4Improved
order of sequential degradation removalUniProcessor · Color saturate + noisePSNR: 24.4 -> 33.9Mixed
replace swin transformer block with large-kernel conv ConvFormer block (ablation)UniProcessor backbone · SIDDPSNR: 39.77 -> 39.81Improved
add VQA module (LLM) to the pipeline (ablation)UniProcessor · ComputeGMACs: 239.83 -> 678.52Hurt
UniProcessor vs PromptIR on gain size by degradation typeUniProcessor · CBSD68 JPEG vs snowPSNR: 0.2dB for JPEG but 5.5dB for snowMixed

Later papers that compared with this method

2 later accepted papers report UniProcessor as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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