AI Paper Atlas

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

OPRO: Orthogonal Panel-Relative Operators for Panel-Aware In-Context Image Generation

Sanghyeon Lee, Minwoo Lee, Euijin Shin, Kangyeol Kim, Seunghwan Choi, Jaegul Choo

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 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 OPRO to LoRA (ComRoPE backbone)LoRA r=8 · Compositional reasoning 4x4accuracy (%): 29.20 -> 47.20Improved
add OPRO to LoRA (RoPE backbone)LoRA r=8 · Compositional reasoning 3x3accuracy (%): 36.20 -> 42.00Improved
add OPRO to LoRA (LieRE backbone)LoRA r=8 · Compositional reasoning 2x2accuracy (%): 58.10 -> 58.10No clear effect
add OPRO to LoRA (APE absolute encoding)LoRA r=8 · Compositional reasoning 4x4accuracy (%): 19.50 -> 24.20Improved
add isometry and same-panel invariance via OPRO instead of additive panel bias (APB) (ablation)LoRA ViT-B · Compositional reasoning 3x3accuracy (%): 35.70 -> 42.00Improved
tie query and key operators (same-panel invariance) instead of Asym-OPRO (ablation)OPRO · Compositional reasoning 3x3accuracy (%): 39.70 -> 42.00Improved
add zero initialization of OPRO (ablation)OPRO · Compositional reasoning 3x3accuracy (%): 38.60 -> 42.00Improved
add OPRO on top of LoRA vs LoRA baseline (additive bias reduces accuracy) (ablation)LoRA · Compositional reasoning 3x3accuracy (%): 36.20 -> 35.70Hurt
add OPRO to ICEditICEdit · MagicBrushL1: 0.1189 -> 0.0781Improved
add OPRO to UNOUNO · MagicBrushDINO: 0.8961 -> 0.8980Improved
add zero initialization (OPRO vs w/o zero init) (ablation)ICEdit + OPRO · MagicBrushDINO: 0.8510 -> 0.8531Improved
add isometry via OPRO instead of additive bias (APB) (ablation)ICEdit · MagicBrushL1: 0.0966 -> 0.0781Improved

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