Astronomical Image Denoising Dataset with 600 Clean/Noisy Pairs

600 pairs of clean and noisy telescope images. The noisy images were generated using physical CCD noise simulation. The dataset was sourced from Kaggle, but the author, organization, and last update date are unknown.

Use Cases

• Train supervised denoising models based on the clean/noisy image pairs.
• Benchmark the performance of noise reduction algorithms on physically simulated CCD noise.
• Develop domain-specific image restoration techniques for astronomical data processing.

Strengths

• Contains 600 image pairs, providing a defined scale for training and evaluation.
• Noise is generated via physical CCD simulation, which likely provides realistic artifacts for the astronomy domain.

Limitations

• Row count and file size are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Kaggle

Collection Method

Images were generated using physical CCD noise simulation.