About

Stanley Ho Chan is an Associate Professor of Electrical & Computer Engineering and Statistics at Purdue University. His research interests include estimation theory, image analysis, machine learning, optimization, sampling theory, and signal and image recovery. He holds a B.Eng. in Electrical Engineering from the University of Hong Kong, an M.A. in Mathematics from the University of California, San Diego, and a Ph.D. in Electrical Engineering from the University of California, San Diego. Dr. Chan completed postdoctoral research at Harvard University. His notable awards include the Croucher Foundation Postdoctoral Research Fellowship in 2012, the Croucher Foundation Ph.D. Scholarship in 2008, the Best Paper Award at the IEEE International Conference on Image Processing in 2016, the HKN Outstanding Teaching Award in 2015, and the Outstanding Graduate Mentor Award from the College of Engineering in 2016.

Research topics

• Computer Science
• Artificial Intelligence
• Mathematics
• Machine Learning
• Computer vision
• Algorithm
• Physics
• Geometry
• Optics
• Mathematical optimization
• Environmental science
• Radiology
• Geology
• Human–computer interaction
• Remote sensing
• Meteorology
• Theoretical computer science

Selected publications

• Pupil Design for Computational Wavefront Estimation

  ArXiv.org · 2026-03-31

  articleOpen accessSenior author

  Establishing a precise connection between imaged intensity and the incident wavefront is essential for emerging applications in adaptive optics, holography, computational microscopy, and non-line-of-sight imaging. While prior work has shown that breaking symmetries in pupil design enables wavefront recovery from a single intensity measurement, there is little guidance on how to design a pupil that improves wavefront estimation. In this work we introduce a quantitative asymmetry metric to bridge this gap and, through an extensive empirical study and supporting analysis, demonstrate that increasing asymmetry enhances wavefront recoverability. We analyze the trade-offs in pupil design, and the impact on light throughput along with performance in noise. Both large-scale simulations and optical bench experiments are carried out to support our findings.

  PublisherOA PDF

• Pupil Design for Computational Wavefront Estimation

  arXiv (Cornell University) · 2026-03-31

  preprintOpen accessSenior author

  Establishing a precise connection between imaged intensity and the incident wavefront is essential for emerging applications in adaptive optics, holography, computational microscopy, and non-line-of-sight imaging. While prior work has shown that breaking symmetries in pupil design enables wavefront recovery from a single intensity measurement, there is little guidance on how to design a pupil that improves wavefront estimation. In this work we introduce a quantitative asymmetry metric to bridge this gap and, through an extensive empirical study and supporting analysis, demonstrate that increasing asymmetry enhances wavefront recoverability. We analyze the trade-offs in pupil design, and the impact on light throughput along with performance in noise. Both large-scale simulations and optical bench experiments are carried out to support our findings.

  PublisherDOI

• Geometric and Quantum Kernel Methods for Predicting Skeletal Muscle Outcomes in chronic obstructive pulmonary disease

  ArXiv.org · 2026-01-01

  articleOpen access

  Quantum methods are increasingly proposed for healthcare, but translational biomarker studies demand transparent benchmarking and robust small-dataset evaluation. We analysed a preclinical COPD cohort of 213 animals with blood and bronchoalveolar-lavage biomarkers to predict tibialis anterior muscle weight, specific force, and muscle quality. We benchmarked tuned classical models against two structured nonlinear low-data strategies: geometry-aware symmetric positive definite (SPD) descriptors, in which training-only clustering maps each subject to Stein-divergence distances from representative prototypes and optional unlabeled synthetic SPD interpolation stabilises prototype discovery; and quantum-kernel regression, including a clustered Nystrom-style feature map that compresses each subject into similarities to a small set of training-derived centres. By replacing full pairwise structure with compact prototype- and centre-based summaries, these steps regularise learning and preserve interpretability in a small-sample setting. Across five outer folds, quantum-kernel ridge regression using four interpretable inputs achieved the best muscle-weight performance (RMSE 4.41 mg; R2 0.62), outperforming a matched compact classical baseline (4.68 mg; R2 0.56). Biomarker-only SPD features also improved over ridge regression (4.55 versus 4.79 mg), and screening evaluation reached ROC-AUC 0.91 for low muscle weight.

  PublisherOA PDF

• Real-Time Markov Modeling for Single-Photon LiDAR: 1000× Acceleration and Convergence Analysis

  2026-04-21

  articleSenior author

  Asynchronous single-photon LiDAR (SP-LiDAR) is an important imaging modality for high-quality 3D applications and navigation, but the modeling of the timestamp distributions of a SP-LiDAR in the presence of dead time remains a very challenging open problem. Prior works have shown that timestamps form a discrete-time Markov chain, whose stationary distribution can be computed as the leading left eigenvector of a large transition matrix. However, constructing this matrix is known to be computationally expensive because of the coupling between states and the dead time. This paper presents the first non-sequential Markov modeling for the timestamp distribution. The key innovation is an equivalent formulation that reparameterizes the integral bounds and separates the effect of dead time as a deterministic row permutation of a base matrix. This decoupling enables efficient vectorized matrix construction, yielding up to 1000× acceleration over existing methods. The new model produces a nearly exact stationary distribution when compared with the gold standard Monte Carlo simulations, yet using a fraction of the time. In addition, a new theoretical analysis reveals the impact of the magnitude and phase of the second-largest eigenvalue, which are overlooked in the literature but are critical to the convergence.

  PublisherDOI

• Geometric and Quantum Kernel Methods for Predicting Skeletal Muscle Outcomes in chronic obstructive pulmonary disease

  arXiv (Cornell University) · 2026-01-01

  preprintOpen access

  Quantum methods are increasingly proposed for healthcare, but translational biomarker studies demand transparent benchmarking and robust small-dataset evaluation. We analysed a preclinical COPD cohort of 213 animals with blood and bronchoalveolar-lavage biomarkers to predict tibialis anterior muscle weight, specific force, and muscle quality. We benchmarked tuned classical models against two structured nonlinear low-data strategies: geometry-aware symmetric positive definite (SPD) descriptors, in which training-only clustering maps each subject to Stein-divergence distances from representative prototypes and optional unlabeled synthetic SPD interpolation stabilises prototype discovery; and quantum-kernel regression, including a clustered Nystrom-style feature map that compresses each subject into similarities to a small set of training-derived centres. By replacing full pairwise structure with compact prototype- and centre-based summaries, these steps regularise learning and preserve interpretability in a small-sample setting. Across five outer folds, quantum-kernel ridge regression using four interpretable inputs achieved the best muscle-weight performance (RMSE 4.41 mg; R2 0.62), outperforming a matched compact classical baseline (4.68 mg; R2 0.56). Biomarker-only SPD features also improved over ridge regression (4.55 versus 4.79 mg), and screening evaluation reached ROC-AUC 0.91 for low muscle weight.

  PublisherDOI

• Diffusion Algorithm for Metalens Optical Aberration Correction

  2026-04-21

  articleOpen access

  Metalenses offer a path toward creating ultra-thin optical systems, but they inherently suffer from severe, spatially varying optical aberrations, especially chromatic aberration, which makes image reconstruction a significant challenge. This paper presents a novel algorithmic solution to this problem, designed to reconstruct a sharp, full-color image from two inputs: a sharp, bandpass-filtered grayscale "structure image" and a heavily distorted "color cue" image, both captured by the metalens system. Our method utilizes a dual-branch diffusion model, built upon a pre-trained Stable Diffusion XL framework, to fuse information from the two inputs. We demonstrate through quantitative and qualitative comparisons that our approach significantly outperforms existing deblurring and pansharpening methods, effectively restoring high-frequency details while accurately colorizing the image.

  PublisherOA PDFDOI

• Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis

  2025-06-10 · 5 citations

  articleSenior author

  Image generation today can produce somewhat realistic images from text prompts. However, if one asks the generator to synthesize a specific camera setting such as creating different fields of view using a 24mm lens versus a 70mm lens, the generator will not be able to interpret and generate scene-consistent images. This limitation not only hinders the adoption of generative tools in professional photography but also highlights the broader challenge of aligning data-driven models with real-world physical settings. In this paper, we introduce Generative Photography, a framework that allows controlling camera intrinsic settings during content generation. The core innovation of this work are the concepts of Dimensionality Lifting and Differential Camera Intrinsics Learning, enabling smooth and consistent transitions across different camera settings. Experimental results show that our method produces significantly more scene-consistent photorealistic images than state-of-the-art models such as Stable Diffusion 3 and FLUX. Our code and additional results are available at https://generativephotography.github.io/project.

  PublisherDOI

• Quanta Diffusion

  2025-08-18

  articleOpen accessSenior author

  We present Quanta Diffusion (QuDi), a powerful generative video reconstruction method for single-photon imaging. QuDI is an algorithm supporting the latest Quanta Image Sensors (QIS) and Single Photon Avalanche Diodes (SPADs) for extremely low-light imaging conditions. Compared to existing methods, QuDi overcomes the difficulties of simultaneously managing the motion and the strong shot noise. The core innovation of QuDi is to inject a physics-based forward model into the diffusion algorithm, while keeping the motion estimation in the loop. QuDi demonstrates an average of 2.4 dB PSNR improvement over the best existing methods.

  PublisherOA PDFDOI

• Astrophotography turbulence mitigation via generative models

  ArXiv.org · 2025-06-03

  preprintOpen accessSenior author

  Photography is the cornerstone of modern astronomical and space research. However, most astronomical images captured by ground-based telescopes suffer from atmospheric turbulence, resulting in degraded imaging quality. While multi-frame strategies like lucky imaging can mitigate some effects, they involve intensive data acquisition and complex manual processing. In this paper, we propose AstroDiff, a generative restoration method that leverages both the high-quality generative priors and restoration capabilities of diffusion models to mitigate atmospheric turbulence. Extensive experiments demonstrate that AstroDiff outperforms existing state-of-the-art learning-based methods in astronomical image turbulence mitigation, providing higher perceptual quality and better structural fidelity under severe turbulence conditions. Our code and additional results are available at https://web-six-kappa-66.vercel.app/

  PublisherOA PDFDOI

• Generative Personalized Blind Face Restoration Enhanced by Physical Identity

  2025-08-18

  articleSenior author

  Facial image restoration plays an essential role in human-related restoration because faces carry significantly more identity information than other body parts. Furthermore, human perception is highly sensitive to facial disharmony, making face restoration critical for applications such as recognition, aesthetics, and overall visual experience. These factors distinguish face restoration from general image restoration tasks. Leveraging the powerful generative capabilities of diffusion models, we propose a robust blind face restoration system that integrates personalized information from personal albums, along with 3D facial geometry and fine-scale surface details derived from the degraded input’s physical identity. Our approach effectively addresses a variety of facial degradations, particularly in severely degraded cases where other blind face restoration methods often fail.

  PublisherDOI

Recent grants

• Short-Exposure Imaging through Atmospheric Turbulence using Single Photon Image Sensors

  NSF · $390k · 2020–2025

• RI: Small: Learning to See Through Atmospheric Turbulence

  NSF · $500k · 2022–2026

• CIF: Small: Signal Processing for Quanta Image Sensors: Reconstruction, Sampling, and Applications

  NSF · $481k · 2017–2021

Frequent coauthors

• Abhiram Gnanasambandam

  Purdue University West Lafayette

  27 shared

• Nicholas Chimitt

  Purdue University West Lafayette

  24 shared

• Truong Q. Nguyen

  22 shared

• Yiheng Chi

  Purdue University West Lafayette

  17 shared

• Omar A. Elgendy

  17 shared

• Zhiyuan Mao

  Samsung (United States)

  16 shared

• Yash Sanghvi

  Samsung (United States)

  13 shared

• Charles A. Bouman

  Purdue University System

  9 shared

Education

• Other, Electrical Engineering

  University of Hong Kong

  2007

• M.A., Mathematics

  University of California, San Diego

  2009

• Ph.D., Electrical Engineering

  University of California, San Diego

  2011

• Other, Electrical Engineering

  Harvard University

  2014

Awards & honors

• Croucher Foundation Postdoctoral Research Fellowship (2012)
• Croucher Foundation Ph.D. Scholarship (2008)
• Best Paper Award, IEEE International Conference on Image Pro…
• HKN Outstanding Teaching Award (2015)
• Outstanding Graduate Mentor Award, College of Engineering (2…