AI Paper Atlas

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

RefDiT: Local Attribute Guidance in Reference-Based Image Generation

Rameshwar Mishra, Srikrishna Karanam, Subramanyam Venkata

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization · 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 SCM attribute-aware triplet conditioning to DreamBooth baseline (M1 to M2) (ablation)DreamBooth-style LoRA · Ablation studyAttr-SIM: 0.43 -> 0.57Improved
add SCM conditioning (M1 to M2) (ablation)DreamBooth-style LoRA · Ablation studyCLIP-I: 0.71 -> 0.77Improved
add SCM conditioning (M1 to M2) (ablation)DreamBooth-style LoRA · Ablation studyCLIP-T: 0.29 -> 0.27Hurt
add triplet-conditioned LoRA training with region consistency loss (M2 to full) (ablation)RefDiT · Ablation studyAttr-SIM: 0.57 -> 0.70Improved
add triplet conditioning (M2 to full) (ablation)RefDiT · Ablation studyCLIP-T: 0.27 -> 0.32Improved
add triplet conditioning (M2 to full) (ablation)RefDiT · Identifier-token attention vs SAM masksmIoU: improves by 0.17Improved
use alpha 0.5 instead of 0.7 (ablation)RefDiT · Ablation studyAttr-SIM: 0.68 -> 0.70Improved
use alpha 0.5 instead of 0.3 (ablation)RefDiT · Ablation studyAttr-SIM: 0.66 -> 0.70Improved
use GPT-4o instead of InternVL for SCM extraction (ablation)RefDiT · Ablation studyAttr-SIM: 0.63 -> 0.70Improved
use GPT-4o instead of InternVL for SCM extraction (ablation)RefDiT · Ablation studyCLIP-I: 0.73 -> 0.80Improved
add SCM conditioning (user study M2 over M1) (ablation)DreamBooth-style LoRA · User studypreference: 72.8%Improved
add triplet conditioning (user study Ours over M2) (ablation)RefDiT · User studypreference: 68.7%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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