Video Diffusion Posterior Sampling for Seeing Beyond Dynamic Scattering Layers

Imaging through scattering is challenging, as even a thin layer can randomly perturb light propagation and obscure hidden objects. Accurate closed-form modeling of forward scattering remains difficult, particularly for dynamically varying or thick layers. Here, we introduce a plug-and-play inverse s...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - PP(2025) vom: 13. Aug.
1. Verfasser: Kwon, Taesung (VerfasserIn)
Weitere Verfasser: Song, Gookho, Kim, Yoosun, Kim, Jeongsol, Ye, Jong Chul, Jang, Mooseok
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2025
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652c 4500
001 NLM391145010
003 DE-627
005 20250814232423.0
007 cr uuu---uuuuu
008 250814s2025 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2025.3598457  |2 doi 
028 5 2 |a pubmed25n1530.xml 
035 |a (DE-627)NLM391145010 
035 |a (NLM)40802634 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Kwon, Taesung  |e verfasserin  |4 aut 
245 1 0 |a Video Diffusion Posterior Sampling for Seeing Beyond Dynamic Scattering Layers 
264 1 |c 2025 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 13.08.2025 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a Imaging through scattering is challenging, as even a thin layer can randomly perturb light propagation and obscure hidden objects. Accurate closed-form modeling of forward scattering remains difficult, particularly for dynamically varying or thick layers. Here, we introduce a plug-and-play inverse solver based on video diffusion models with a physically grounded forward model tailored to dynamic scattering layers. Our method extends Diffusion Posterior Sampling (DPS) to the spatio-temporal domain, thereby capturing statistical correlations between video frames and scattered signals more effectively. Leveraging these temporal correlations, our approach recovers high-resolution spatial details that spatial-only methods typically fail to reconstruct. We also propose an inference-time optimization with a lightweight mapping network, enabling joint estimation of low-dimensional forward-model parameters without additional training. This joint optimization significantly enhances adaptability to unknown, time-varying degradations, making our method suitable for blind inverse scattering problems. We validate across diverse conditions, including different scene types, layer thicknesses, and scene-layer distances. And real-world experiments using multiple datasets confirm the robustness and effectiveness of our approach, even under real noise and forward-model approximation mismatches. Finally, we validate our method as a general video-restoration framework across dehazing, deblurring, inpainting, and blind restoration under complex optical aberrations. Our implementation is available at: https://github.com/star-kwon/VDPS 
650 4 |a Journal Article 
700 1 |a Song, Gookho  |e verfasserin  |4 aut 
700 1 |a Kim, Yoosun  |e verfasserin  |4 aut 
700 1 |a Kim, Jeongsol  |e verfasserin  |4 aut 
700 1 |a Ye, Jong Chul  |e verfasserin  |4 aut 
700 1 |a Jang, Mooseok  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g PP(2025) vom: 13. Aug.  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:PP  |g year:2025  |g day:13  |g month:08 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2025.3598457  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d PP  |j 2025  |b 13  |c 08