AI Paper Atlas

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

PureCC: Pure Learning for Text-to-Image Concept Customization

Zhichao Liao, Xiaole Xian, Qingyu Li, Wenyu Qin, Meng Wang, Weicheng Xie, Siyang Song, Pingfa Feng, Long Zeng, Liang Pan

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Multi-concept composition · 1 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 L_PureCC loss to L_CC (ablation)PureCC · DreamBenchPCC (instance)Seg-Cons: 23.74 -> 69.37Improved
add L_PureCC loss to L_CC (ablation)PureCC · DreamBenchPCC (instance)dCLIP-T (base): -4.52 -> -0.31Improved
add L_PureCC loss to L_CC (ablation)PureCC · DreamBenchPCC (instance)CLIP-I (target): 0.65 -> 0.81Improved
add separate pre-fine-tuned frozen extractor (two-stage) instead of merged training (ablation)PureCC · DreamBenchPCC (instance)CLIP-I (target): 0.50 -> 0.81Improved
add separate pre-fine-tuned frozen extractor (two-stage) instead of merged training (ablation)PureCC · DreamBenchPCC (instance)Seg-Cons: 54.37 -> 69.37Hurt
use adaptive lambda* instead of fixed lambda=1.0 (ablation)PureCC · DreamBenchPCC (instance)CLIP-I (target): 0.43 -> 0.81Improved
use adaptive lambda* instead of fixed lambda=5.0 (ablation)PureCC · DreamBenchPCC (instance)dCLIP-T (base): -2.67 -> -0.31Improved
use adaptive lambda* instead of fixed lambda=3.0 (ablation)PureCC · DreamBenchPCC (style)CSD: 0.61 -> 0.63Improved
raise eta from 0.5 to 1.0 (ablation)PureCC · DreamBenchPCC (instance)CLIP-I (target): 0.55 -> 0.81Improved
raise eta from 1.0 to 2.0 (ablation)PureCC · DreamBenchPCC (instance)CLIP-I (target): 0.81 -> 0.67Hurt
raise eta from 1.0 to 1.5 (ablation)PureCC · DreamBenchPCC (instance)CLIP-I (target): 0.81 -> 0.80No clear effect
use trainable model's own base-text prediction as original prediction instead of extra frozen model (ablation)PureCC · DreamBenchPCC (qualitative)visual qualityNo clear effect

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