AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

S2R-HDR: A Large-Scale Rendered Dataset for HDR Fusion

Yujin Wang, Jiarui Wu, Yichen Bian, Fan Zhang, Tianfan Xue

ICLR 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation

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
pretrain on S2R-HDR then adapt with S2R-Adapter instead of training on Challenge123 onlySAFNet · Challenge123PSNR-mu: 41.88 -> 43.43Improved
pretrain on S2R-HDR then adapt with S2R-Adapter instead of training on SCT onlySCTNet · SCTPSNR-mu: 42.55 -> 43.24Improved
train on synthetic S2R-HDR instead of real SCT for cross-dataset testingSAFNet · Challenge123PSNR-mu: 34.26 -> 42.75Improved
train on S2R-HDR instead of Challenge123 when testing on SCTSAFNet · SCTPSNR-mu: 35.14 -> 34.89Hurt
add test-time adaptation with S2R-Adapter on top of S2R-HDR pretrainingSAFNet · SCT (no GT)PSNR-mu: 34.89 -> 36.28Improved
add test-time adaptation with S2R-AdapterSAFNet · SCT (no GT)PSNR-l: 43.85 -> 47.23Improved
add S2R-Adapter to SAFNet instead of simple fine-tuning to reduce forgetting (ablation)SAFNet · S2R-HDR train set after SCT adaptationPSNR-mu: 35.52 -> 35.95Improved
use S2R-Adapter instead of fine-tuning (ablation)SCTNet · Challenge123PSNR-mu: 42.1 -> 42.58Improved
use S2R-Adapter instead of fine-tuning (ablation)SAFNet · SCTPSNR-mu: 43.03 -> 43.33Improved
add shared and transfer branches individually vs together (ablation)S2R-Adapter on SAFNet · SCTPSNR-muImproved
add teacher-student framework and uncertainty-based scale adjustment to test-time adaptation (ablation)S2R-Adapter · SCTPSNRImproved
pretrain on S2R-HDR rather than Challenge123 before adapting with S2R-Adapter (ablation)SAFNet · SCTPSNR-mu: 42.92 -> 43.44Improved

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