{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/simple-base-frame-guided-residual-network-for","title":"Simple Base Frame Guided Residual Network for RAW Burst Image Super-Resolution","arxiv_id":null,"date":"2024-02-27","proceeding":"VISAPP 2024 2","authors":["Anderson Cotrim","Gerson Barbosa","Cid Santos","Helio Pedrini"],"abstract":"Burst super-resolution or multi-frame super-resolution (MFSR) has gained significant attention in recent years, particularly in the context of mobile photography. With modern handheld devices consistently increasing their processing power and the ability to capture multiple images even faster, the development of robust MFSR algorithms has become increasingly feasible. Furthermore, in contrast to extensively studied single-image super-resolution (SISR), burst super-resolution mitigates the ill-posed nature of reconstructing high-resolution images from low-resolution ones by merging information from multiple shifted frames. This research introduces a novel and effective deep learning approach, SBFBurst, designed to tackle this challenging problem. Our network takes multiple noisy RAW images as input and generates a denoised, super-resolved RGB image as output. We demonstrate that significant enhancements can be achieved in this problem by incorporating base frame-guided mechanisms through operations such as feature map concatenation and skip connections. Additionally, we highlight the significance of employing mosaicked convolution to enhance alignment, thus enhancing the overall network performance in super-resolution tasks. These relatively simple improvements underscore the competitiveness of our proposed method when compared to other state-of-the-art approaches.","url_abs":"https://www.scitepress.org/PublishedPapers/2024/123483/","url_pdf":"https://www.scitepress.org/Papers/2024/123483/123483.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"simple-base-frame-guided-residual-network-for","repo_url":"https://github.com/AndersonCotrim/SBFBurst","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"burst-image-super-resolution","task_name":"Burst Image Super-Resolution"},{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"multi-frame-super-resolution","task_name":"Multi-Frame Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/burst-image-super-resolution-on-burstsr","task":"Burst Image Super-Resolution","dataset":"BurstSR","model":"SBFBurst","rank_in_archive_order":2,"of":9,"metrics":{"LPIPS":"0.022","PSNR":"48.87","SSIM":"0.987"},"uses_additional_data":false},{"leaderboard":"/sota/burst-image-super-resolution-on","task":"Burst Image Super-Resolution","dataset":"SyntheticBurst","model":"SBFBurst","rank_in_archive_order":5,"of":8,"metrics":{"LPIPS":"0.036","PSNR":"42.19","SSIM":"0.968"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}