AI Paper Atlas

Research map / Image generation / Editing and style transfer

RCEdit-500K: Reference Completion for Image-Conditioned Image Editing

Jingxu Zhang, Daneul Kim, Yueming Pan, DONG CHEN, Kai Qiu, Yang Liu, Yifan Yang, Qi Dai, Xiaoyan Sun, Chong Luo

ECCV 2026 · Image generation › Editing and style transfer · approach: Instruction-based diffusion editing · 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
fine-tune with RCEdit-500K via LoRAFlux-Kontext · MultiBanana two-referenceAvg: 2.82 -> 4.04Improved
fine-tune with RCEdit-500K via LoRAQwen-Image-Edit-2509 · MultiBanana two-referenceAvg: 4.31 -> 4.56Improved
full fine-tune Janus-Pro on RCEdit-500KJanus-Pro · MultiBanana two-referenceAvg: 1.03 -> 4.43Improved
add five-dimensional VLM post-filtering (ablation)RCEdit-500K Flux-Kontext LoRA · MultiBanana two-reference (Flux-Kontext LoRA)Avg: 3.62 -> 4.04Improved
add five-dimensional VLM post-filtering (ablation)RCEdit-500K Flux-Kontext LoRA · MultiBanana two-reference (Flux-Kontext LoRA)BSM: 3.62 -> 4.76Improved
add weak-instruction augmentation (ablation)RCEdit-500K Flux-Kontext LoRA · MultiBanana two-reference (Flux-Kontext LoRA)Avg: 3.74 -> 4.04Improved
add weak-instruction augmentation (ablation)RCEdit-500K Flux-Kontext LoRA · MultiBanana two-reference (Flux-Kontext LoRA)IA: 3.67 -> 3.52Hurt
add weak-instruction augmentation (ablation)RCEdit-500K Flux-Kontext LoRA · MultiBanana two-reference (Flux-Kontext LoRA)RC: 3.35 -> 3.42Improved
train on ImgEdit ICIE subsetFlux-Kontext LoRA · MultiBanana two-referenceAvg: 2.82 -> 2.92Improved
train on AnyEdit ICIE subsetFlux-Kontext LoRA · MultiBanana two-referenceIA: 2.94 -> 2.17Hurt
train on AnyEdit ICIE subsetFlux-Kontext LoRA · MultiBanana two-referenceBSM: 2.39 -> 4.55Improved
train on RCEdit-60K instead of AnyEdit/ImgEditFlux-Kontext LoRA · MultiBanana two-referenceAvg: 2.97 -> 3.68Improved

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