AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

RDF-MIG: A Robust Diffusion Framework for Masked Image Generation to Augment Semantic Segmentation and Change Detection

Zian Cao, Wei Wei, Qingshan Gao, Yuanyuan Fu

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Retrieval and matching with generative features

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 diffusion with MCRD loss instead of MSE (ablation)RDF-MIG · Hi-CNA (SS) image qualityFID: 35.23 -> 27.38Improved
train diffusion with MCRD loss instead of MSE (ablation)RDF-MIG · WHU Building image qualityFID: 47.16 -> 17.05Improved
train diffusion with MCRD loss instead of MSE (ablation)RDF-MIG · Hi-CNA (CD) image qualityFID: 36.01 -> 29.85Improved
train diffusion with MCRD loss instead of MSE (ablation)RDF-MIG synthetic data · Hi-CNA (SS), U-NetIoU: 42.28 -> 44.13Improved
train diffusion with MCRD loss instead of MSE (ablation)RDF-MIG synthetic data · Hi-CNA (CD), SNU-NetIoU: 45.62 -> 50.00Improved
use Huber loss instead of MSE (ablation)RDF-MIG synthetic data · Hi-CNA (SS), U-NetIoU: 42.28 -> 42.97Improved
use MCRD instead of Huber loss (ablation)RDF-MIG synthetic data · Hi-CNA (CD), SNU-NetIoU: 46.31 -> 50.00Improved
15% label noise with MSE loss (ablation)RDF-MIG synthetic data · Hi-CNA (SS), U-NetIoU: -2.51 (39.77)Hurt
15% label noise with MCRD loss (ablation)RDF-MIG synthetic data · Hi-CNA (SS), U-NetIoU: -0.28 (43.85)No clear effect
add NIR band generation (multispectral) (ablation)RDF-MIG · Hi-CNA (SS), U-NetIoU: 44.13 -> 45.20Improved
add NIR band generation (multispectral) (ablation)RDF-MIG · Hi-CNA (CD), SNU-NetIoU: 50.00 -> 51.07Improved
add synthetic data to real training set at increasing proportions (ablation)U-Net / SNU-Net · Hi-CNA and WHU BuildingIoUImproved

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