POLARIS: A High-contrast Polarimetric Imaging Benchmark Dataset for Exoplanetary Disk Representation Learning

2025-06-04

AI Summary

Direct imaging of Earth-like exoplanets suffers from excessive reliance on artificial reference stars for calibration and insufficient characterization capability for circumstellar disk structures. Method: We construct the first high-quality, standardized polarimetric imaging benchmark dataset—comprising all publicly available SPHERE/IRDIS polarimetric data from 2014–2023 (>1 million frames)—reducing manual calibration dependency to <10%. We further propose the first unsupervised generative representation learning framework tailored for exoplanet imaging, integrating statistical modeling, generative modeling, and vision-language priors to enable multimodal disk structure representation. Contribution/Results: Our framework achieves significant improvements over state-of-the-art methods in disk classification and reconstruction tasks. It establishes a scalable, low-dependency paradigm for detecting Earth-like planets under low signal-to-noise ratio and weak polarization conditions, advancing robust, calibration-efficient exoplanet imaging.

Technology Category

• Computer Vision: Representation Learning for Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

With over 1,000,000 images from more than 10,000 exposures using state-of-the-art high-contrast imagers (e.g., Gemini Planet Imager, VLT/SPHERE) in the search for exoplanets, can artificial intelligence (AI) serve as a transformative tool in imaging Earth-like exoplanets in the coming decade? In this paper, we introduce a benchmark and explore this question from a polarimetric image representation learning perspective. Despite extensive investments over the past decade, only a few new exoplanets have been directly imaged. Existing imaging approaches rely heavily on labor-intensive labeling of reference stars, which serve as background to extract circumstellar objects (disks or exoplanets) around target stars. With our POLARIS (POlarized Light dAta for total intensity Representation learning of direct Imaging of exoplanetary Systems) dataset, we classify reference star and circumstellar disk images using the full public SPHERE/IRDIS polarized-light archive since 2014, requiring less than 10 percent manual labeling. We evaluate a range of models including statistical, generative, and large vision-language models and provide baseline performance. We also propose an unsupervised generative representation learning framework that integrates these models, achieving superior performance and enhanced representational power. To our knowledge, this is the first uniformly reduced, high-quality exoplanet imaging dataset, rare in astrophysics and machine learning. By releasing this dataset and baselines, we aim to equip astrophysicists with new tools and engage data scientists in advancing direct exoplanet imaging, catalyzing major interdisciplinary breakthroughs.

Problem

• AI for imaging Earth-like exoplanets using polarimetric data
• Reducing manual labeling in exoplanetary disk detection
• Benchmarking models for direct exoplanet imaging representation learning

Innovation

• High-contrast polarimetric imaging dataset
• Unsupervised generative representation learning framework
• Reduced manual labeling to under 10 percent