datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
Lowlight-Smartphone-Dataset
[WACV'26] Low-light Smartphone Dataset (LSD)
This is the official dataset proposed in our paper titled "Illuminating Darkness: Learning to Enhance Low-light Images In-the-Wild"
📄 Paper: arXiv💻 Code: GitHub - LSD-TFFormer
Overview
We introduce LSD, the largest in-the-wild Single-Shot Low-Light Image Enhancement (SLLIE) dataset to date.
Dataset Structure
This repository contains the following training data files:
patch_DLL_gtPatch.tar.gz… See the full description on the dataset page: https://huggingface.co/datasets/ARM4588/Lowlight-Smartphone-Dataset.low-light-project
Low-Light Restoration Dataset
Paired low-light / normal-light image patches for training and evaluation.
Contents of low-light.tar
low-light/
├── train/ 30,000 paired patches (60,000 files)
├── val/ 1,000 paired patches (2,000 files)
├── test/ 1,000 input patches (no ground truth)
└── dataset.py reference PyTorch Dataset (Python 3.10+)
All images are lossless WebP (.webp).
File naming
Every image is named… See the full description on the dataset page: https://huggingface.co/datasets/KBlueLeaf/low-light-project.