AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Object Fidelity Diffusion for Remote Sensing Image Generation

Ziqi Ye, Shuran Ma, Jie Yang, Xiaoyi Yang, Yi Yang, Ziyang Gong, Xue Yang, Haipeng Wang

ICLR 2026 · Image generation › Autoregressive and latent generation · approach: Compositional scene generation · 2 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 enhanced shape generation module (ESGM) (ablation)OF-Diff · DIORFID: 42.59 -> 24.87Improved
add ESGM (ablation)OF-Diff · DIORYOLOScore: 41.20 -> 55.08Improved
add online-distillation consistency loss L_c (ablation)OF-Diff · DIORFID: 42.59 -> 36.25Improved
add DDPO fine-tuning to full model with ESGM and L_c (ablation)OF-Diff · DIORmAP50: 54.31 -> 54.44Improved
add DDPO fine-tuning (ablation)OF-Diff with ESGM and L_c · DIORFID: 24.98 -> 24.92No clear effect
add DDPO alone without ESGM (ablation)OF-Diff · DIORmAP50: 52.13 -> 53.41Improved
add captions as conditioning input (ablation)OF-Diff · DIORDelta mAP50: -1.15Hurt
add captions as conditioning input (ablation)OF-Diff · DIOR aesthetic preferencepreference rate: Q2 caption 11.21 vs 8.79; Q1 realism 6.57 vs 13.43Mixed
replace real training data with only generated data (ablation)OF-Diff · DIORmAP: 52.84 -> 45.67Hurt
add generated data on top of real data (up to 300%) (ablation)OF-Diff · DIORmAP: 52.84 -> 54.82Improved
use OF-Diff instead of CC-Diff on HRSC2016 for CMMD/CAS/YOLOScoreOF-Diff · HRSC2016YOLOScore: 32.42 -> 30.97Hurt
use OF-Diff instead of CC-Diff on DIOR for CASOF-Diff · DIORCAS: 82.61 -> 82.55No clear effect

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