HazeSpace2M: Large-scale Single Image Dehazing Dataset

HazeSpace2M is a collection of over 2 million images designed to enhance dehazing through haze type classification. HazeSpace2M includes diverse scenes with 10 haze intensity levels, featuring Fog, Cloud, and Environmental Haze.

[Dataset] [Paper] [BibTeX]
@inproceedings{Tanvir2024hazespace2m,
  title={HazeSpace2M: A Dataset for Haze Aware Single Image Dehazing},
  author={Islam, Md Tanvir and Rahim, Nasir and Anwar, Saeed and Saqib Muhammad},
  booktitle={Proceedings of the 32nd ACM International Conference on Multimedia},
  year={2024},
  doi={10.1145/3664647.3681382}
}

LoLI-Street: Low-light Image Enhancement Dataset

The training consists of 30k, while validation has 3k paired low and high-light images. Moreover, we collected high-resolution videos (4K/8K at 60fps) from various cities under low-light conditions, extracting and manually reviewing frames to create the Real Low-light Testset (RLLT) of our LoLI-Street dataset. We used Photoshop v25.0 to generate the synthetic images of our dataset.

[Dataset] [Paper] [BibTeX]
@InProceedings{Islam_2024_ACCV, author = {Islam, Md Tanvir and Alam, Inzamamul and Woo, Simon S. and Anwar, Saeed and Lee, IK Hyun and Muhammad, Khan}, title = {LoLI-Street: Benchmarking Low-light Image Enhancement and Beyond}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1250-1267} }

CDC: Crop Damage Classification

CDC features train set contains 21k images of damaged and non-damaged classes of crops and a testset that contains 2k images each class having 1k images. In total it features 23k images suitable for training and testing models for identifying damaged crops effectively.

[Dataset] [Paper] [BibTeX]
@article{islam2025resource, title={Resource constraint crop damage classification using depth channel shuffling}, author={Islam, Md Tanvir and Swapnil, Safkat Shahrier and Billal, Md Masum and Karim, Asif and Shafiabady, Niusha and Hassan, Md Mehedi}, journal={Engineering Applications of Artificial Intelligence}, volume={144}, pages={110117}, year={2025}, publisher={Elsevier} }