P-NLOS: A Prompt-Based Method for Robust NLOS Imaging

Simple item page
dc.contributor.authorSu, Xiongfeien_US
dc.contributor.authorZhu, Tianyien_US
dc.contributor.authorLiu, Linaen_US
dc.contributor.authorZhang, Yuanlongen_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:04:45Z
dc.date.available2024-10-13T18:04:45Z
dc.date.issued2024
dc.description.abstractThe field of non-line-of-sight (NLOS) imaging is experiencing rapid advancement, offering the potential to reveal hidden scenes that are otherwise obscured from direct view. Despite this promise, NLOS systems face obstacles in managing a variety of sampling noise, as well as spatial and temporal variations, which limit their practical deployment. This paper introduces a novel strategy to overcome these challenges. It employs prompts to encode latent information, which is then leveraged to dynamically guide the NLOS reconstruction network. The proposed method, P-NLOS, consists of two branches: a reconstruction branch that handles the restoration of sampled information, and a prompting branch that captures the original information. The prompting branch supplies reliable content to the reconstruction branch, thereby enhancing the guidance of the reconstruction process and enhancing the quality of the recovered images. Overall, P-NLOS demonstrates robustness in real-world applications by effectively handling a wide range of corruption types in NLOS reconstruction tasks, including varying noise levels, diverse blur kernels, and temporal resolution variations.en_US
dc.description.sectionheadersImage Processing and Filtering I
dc.description.seriesinformationPacific Graphics Conference Papers and Posters
dc.identifier.doi10.2312/pg.20241303
dc.identifier.isbn978-3-03868-250-9
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20241303
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20241303
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Computational photography
dc.subjectComputing methodologies → Computational photography
dc.titleP-NLOS: A Prompt-Based Method for Robust NLOS Imagingen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
pg20241303.pdf
Size:
4.79 MB
Format:
Adobe Portable Document Format
Download
Collections
PG2024 Conference Papers and Posters