{"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/illuminating-darkness-enhancing-real-world","title":"Illuminating Darkness: Enhancing Real-world Low-light Scenes with Smartphone Images","arxiv_id":"2503.06898","date":"2025-03-10","proceeding":null,"authors":["S M A Sharif","Abdur Rehman","Zain Ul Abidin","Rizwan Ali Naqvi","Fayaz Ali Dharejo","Radu Timofte"],"abstract":"Digital cameras often struggle to produce plausible images in low-light conditions. Improving these single-shot images remains challenging due to a lack of diverse real-world pair data samples. To address this limitation, we propose a large-scale high-resolution (i.e., beyond 4k) pair Single-Shot Low-Light Enhancement (SLLIE) dataset. Our dataset comprises 6,425 unique focus-aligned image pairs captured with smartphone sensors in dynamic settings under challenging lighting conditions (0.1--200 lux), covering various indoor and outdoor scenes with varying noise and intensity. We extracted and refined around 180,000 non-overlapping patches from 6,025 collected scenes for training while reserving 400 pairs for benchmarking. In addition to that, we collected 2,117 low-light scenes from different sources for extensive real-world aesthetic evaluation. To our knowledge, this is the largest real-world dataset available for SLLIE research. We also propose learning luminance-chrominance (LC) attributes separately through a tuning fork-shaped transformer model to enhance real-world low-light images, addressing challenges like denoising and over-enhancement in complex scenes. We also propose an LC cross-attention block for feature fusion, an LC refinement block for enhanced reconstruction, and LC-guided supervision to ensure perceptually coherent enhancements. We demonstrated our method's effectiveness across various hardware and scenarios, proving its practicality in real-world applications. Code and dataset available at https://github.com/sharif-apu/LSD-TFFormer.","url_abs":"https://arxiv.org/abs/2503.06898v1","url_pdf":"https://arxiv.org/pdf/2503.06898v1.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":"illuminating-darkness-enhancing-real-world","repo_url":"https://github.com/sharif-apu/lsd-tfformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"4k","task_name":"4k"},{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"low-light-image-enhancement","task_name":"Low-Light Image Enhancement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}