AI Paper Atlas

Research map / Image generation / Image restoration

MMAIF: Multi-task and Multi-degradation All-in-One for Image Fusion with Language Guidance

Zihan Cao, Yu Zhong, Ziqi Wang, Liang-Jian Deng

ICCV 2025 · Image generation › Image restoration · approach: Efficient restoration architectures · 11 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 MoE GLU in place of dense FFN (ablation)MMAIF DiT (FM) · LLVIP degraded VIFVIF: 0.436 -> 0.582Improved
use DiT backbone instead of U-net at similar parameter count (ablation)MMAIF (FM) · LLVIP degraded VIFVIF: 0.423 -> 0.436Improved
add 2D RoPE and per-block absolute PE (ablation)MMAIF DiT · LLVIP degraded VIFVIF: 0.582 -> 0.593Improved
add attention value residual (ablation)MMAIF DiT · LLVIP degraded VIFVIF: 0.593 -> 0.599Improved
add NAFBlock convolution before attention (ablation)MMAIF DiT · LLVIP degraded VIFVIF: 0.599 -> 0.607Improved
add LoRA-AdaLN conditioning (ablation)MMAIF DiT · LLVIP degraded VIFVIF: 0.607 -> 0.604No clear effect
use 100 Euler steps instead of 25 (ablation)MMAIF (FM) · LLVIP degraded VIFVIF: 0.592 -> 0.605Improved
use Gaussian prior p0 instead of degraded latent Z0 (ablation)MMAIF (FM) · LLVIP degraded VIFVIF: 0.435 -> 0.604Improved
use stochastic I2SB sampling with p0=mean instead of deterministic p0=mean (ablation)MMAIF (FM) · LLVIP degraded VIFVIF: 0.438 -> 0.601Improved
use Cosmos VAE tokenizer instead of Flux KL-VAE (ablation)MMAIF latent space · SICE+LLVIP reconstructionPSNR: 33.41 -> 34.02Improved
use flow matching instead of regressionMMAIF · LLVIP degraded VIFVIF: 0.556 -> 0.604Improved
use all-in-one MMAIF instead of DA-CLIP+EMMA restoration+fusion under three simultaneous degradationsMMAIF · LLVIP multi-degradation (n=3)VIF: 0.431 -> 0.584Improved

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