# A New Statistical Model of Star Speckles for Learning to Detect and Characterize Exoplanets in Direct Imaging Observations

arXiv: https://arxiv.org/abs/2503.17117 · HTML: https://mlsanity.com/paper/2503.17117/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 75 references that are in the map.
- First posted on arXiv 21 Mar 2025.

## Builds on (most cited first, 9 of 9)

- [Non-negative Matrix Factorization: Robust Extraction of Extended Structures](https://mlsanity.com/paper/1712.10317/) (2017)
- [Using Data Imputation for Signal Separation in High Contrast Imaging](https://mlsanity.com/paper/2001.00563/) (2020)
- [deep PACO: Combining statistical models with deep learning for exoplanet detection and characterization in direct imaging at high contrast](https://mlsanity.com/paper/2303.02461/) (2023)
- [Half-sibling regression meets exoplanet imaging: PSF modeling and subtraction using a flexible, domain knowledge-driven, causal framework](https://mlsanity.com/paper/2204.03439/) (2022)
- [A Possible Converter to Denoise the Images of Exoplanet Candidates through Machine Learning Techniques](https://mlsanity.com/paper/2301.04292/) (2023)
- [NA-SODINN: a deep learning algorithm for exoplanet image detection based on residual noise regimes](https://mlsanity.com/paper/2302.02854/) (2023)
- [Combining multi-spectral data with statistical and deep-learning models for improved exoplanet detection in direct imaging at high contrast](https://mlsanity.com/paper/2306.12266/) (2023)
- [Shrinkage MMSE estimators of covariances beyond the zero-mean and stationary variance assumptions](https://mlsanity.com/paper/2403.07104/) (2024)
- [MODEL&CO: Exoplanet detection in angular differential imaging by learning across multiple observations](https://mlsanity.com/paper/2409.17178/) (2024)

## Abstract (arXiv)

The search for exoplanets is an active field in astronomy, with direct imaging as one of the most challenging methods due to faint exoplanet signals buried within stronger residual starlight. Successful detection requires advanced image processing to separate the exoplanet signal from this nuisance component. This paper presents a novel statistical model that captures nuisance fluctuations using a multi-scale approach, leveraging problem symmetries and a joint spectral channel representation grounded in physical principles. Our model integrates into an interpretable, end-to-end learnable framework for simultaneous exoplanet detection and flux estimation. The proposed algorithm is evaluated against the state of the art using datasets from the SPHERE instrument operating at the Very Large Telescope (VLT). It significantly improves the precision-recall trade-off, notably on challenging datasets that are otherwise unusable by astronomers. The proposed approach is computationally efficient, robust to varying data quality, and well suited for large-scale observational surveys.