AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Enlightening Photographic Style Transfer with a Self-Supervised Photographic Embedding

Chengxuan Zhu, Jiacong Fang, Shuchen Weng, Youwei Lyu, Jiajun Tang, Qingnan Fan, Chao Xu, Boxin Shi

ECCV 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 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
use CIE-Lab instead of RGB color space (ablation)PETAL embedding · PPR10K subset retrievalR@1: 70.34 -> 74.27Improved
use CIE-Lab instead of RGB color space (ablation)PETAL · PST50 style transferPSNR: 22.22 -> 24.63Improved
add cross-attention histogram injection (ablation)PETAL embedding · PPR10K subset retrievalR@1: 68.93 -> 74.27Improved
add cross-attention histogram injection (ablation)PETAL · PST50 style transferPSNR: 22.24 -> 24.63Improved
use adaptive pooling instead of mean pooling (ablation)PETAL embedding · PPR10K subset retrievalR@1: 68.91 -> 74.27Improved
add pooled patch features to the CLS token (ablation)PETAL embedding · PPR10K subset retrievalR@1: 73.74 -> 74.27Improved
add pooled patch features to the CLS token (ablation)PETAL · PST50 style transferPSNR: 23.11 -> 24.63Improved
add histogram reconstruction loss (ablation)PETAL embedding · PPR10K subset retrievalR@1: 66.98 -> 74.27Improved
add histogram reconstruction loss (ablation)PETAL · PST50 style transferLPIPS: 0.1354 -> 0.1021Improved
add intra-sample loss (ablation)PETAL embedding · PPR10K subset retrievalR@1: 36.09 -> 74.27Improved
add inter-sample loss with hard negatives (ablation)PETAL embedding · PPR10K subset retrievalR@1: 67.53 -> 74.27Improved
fine-tune DINOv3 with the same data and objectivesDINOv3 · PPR10K subset retrievalR@1: 1.48 -> 59.30Improved

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