A new benchmark and baseline for real-time high-resolution image inpainting on edge devices

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Sánchez-Ortega, Marcelo
• dc.contributor.author Triginer-Garces, Gil
• dc.contributor.author Ballester, Coloma
• dc.contributor.author Sarasua, Ignacio
• dc.contributor.author Raad, Lara
• dc.date.accessioned 2025-03-24T14:22:26Z
• dc.date.available 2025-03-24T14:22:26Z
• dc.date.issued 2025
• dc.description.abstract Existing image inpainting methods have shown impressive completion results for low-resolution images. However, most of these algorithms fail at high resolutions and require powerful hardware, limiting their deployment on edge devices. Motivated by this, we propose the first baseline for REal-Time High Resolution image INpainting on Edge Devices (RETHINED) that is able to inpaint at ultra-high-resolution and can run in real-time (≤ 30ms) in a wide variety of mobile devices. A simple, yet effective novel method formed by a lightweight Convolutional Neural Network (CNN) to recover structure, followed by a resolution-agnostic patch replacement mechanism to provide detailed texture. Specially our pipeline leverages the structural capacity of CNN and the high-level detail of patch-based methods, which is a key component for highresolution image inpainting. To demonstrate the real application of our method, we conduct an extensive analysis on various mobile-friendly devices and demonstrate similar inpainting performance while being 100 × faster than existing state-of-the-art methods. Furthemore, we realease DF8K-Inpainting, the first free-form mask UHD inpainting dataset.
• dc.description.sponsorship This project is supported by MICINN/FEDER UE project ref. PID2021-127643NB-I00 and Doctorals Industrials ref. DI 2022 075 founded by the Government of Catalonia
• dc.format.mimetype application/pdf
• dc.identifier.citation Sánchez-Ortega M, Ballester C, Triginer-Garces G, Raad L, Sarasua I. A new benchmark and baseline for real-time high-resolution image inpainting on edge devices. Paper presented at: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025; 2025 Feb 28 - Mar 4; Tucson, USA. 11 p.
• dc.identifier.uri http://hdl.handle.net/10230/69997
• dc.language.iso eng
• dc.publisher Institute of Electrical and Electronics Engineers (IEEE)
• dc.relation.projectID info:eu-repo/grantAgreement/ES/3PE/PID2021-127643
• dc.rights © 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. http://dx.doi.org/[núm.DOI]
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Real-time inpainting
• dc.subject.keyword Edge devices
• dc.subject.keyword Inpainting
• dc.subject.keyword High-resolution inpainting
• dc.title A new benchmark and baseline for real-time high-resolution image inpainting on edge devices
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/acceptedVersion