AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

MMPD-Bench: Bridging Multimodal Fission with Multi-Polarimetric Modalities Decomposition

Yi He, Zimo Zhao, Yiming Yang, Xiaoyuan Cheng, Chao He, Yukun Hu

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion

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
Scale model from small (-s) to base (-b)Mamba SwinUMamba · MMPD-Bench under Gaussian noise (ImageD)PSNR relative degradation (%): 6.3 -> 11.5Hurt
Scale model from small (-s) to base (-b)Transformer FactFormer · MMPD-Bench under Gaussian noise (ImageD)PSNR relative degradation (%): 0.7 -> 8.4Hurt
Scale model from small (-s) to base (-b)Transformer SwinUnet · MMPD-Bench under Gaussian noise (ImageD)PSNR relative degradation (%): 1.0 -> 2.8Hurt
Scale model from small (-s) to base (-b)FNO · MMPD-Bench under Gaussian noise (ImageD)PSNR relative degradation (%): 1.2 -> 0.2No clear effect
Use U-shaped neural operator UNO-b instead of non-U FNO-bNeural operators · MMPD-Bench under Gaussian noise (ImageTheta)PSNR relative degradation (%): 44.8 -> 49.8Hurt
Use transformer SwinUnet instead of MambaSwinUnet-s vs SwinUMamba-s · MMPD-Bench under Gaussian noise (ImageTheta)PSNR relative degradation (%): 26.1 -> 1.4Improved
Add Gaussian measurement noise to training and test dataDDIM-s · MMPD-Bench under Gaussian noise (ImageD)PSNR relative degradation (%): -82.1Improved
Add Gaussian measurement noise to training and test dataDDPM-b · MMPD-Bench under Gaussian noise (ImageD)PSNR relative degradation (%): -21.5Improved
Add Gaussian measurement noise to training and test dataDDIM-b · MMPD-Bench under Gaussian noise (ImageTheta)SSIM relative degradation (%): 65.9Hurt
Use spectral parameterization (FactFormer, Neural Operators) instead of patch attention or SSMsAngular phase recovery · MMPD-Bench ImageTheta and ImagePsi (clear)PSNR (dB): 27.3 dB (UNO-b ImageTheta), 52.5 dB (FF-b ImagePsi)Improved
Use diffusion models instead of deterministic surrogatesDiffusion vs FNO/FactFormer/SwinUMamba · MMPD-Bench fidelity and physical consistency (clear)fidelity and retardance consistencyHurt

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