|
|
|
|
| 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
|