logo 

Welcome

Welcome to Purdue Intelligent Imaging Lab (i2Lab).

Our research mission is to advance computational imaging techniques for seeing in adverse environments. The core mathematical problem we study is how to recover signals in a very low signal-to-noise regime. We have expertise in wave optics, photon statistics, optimization algorithms, and theoretical machine learning. We develop numerical simulators, theoretical analysis, and deep learning algorithms for image reconstruction problems. Specific research topics include:

Follow us

We are hiring!

Postdoc Opening (2021-2022)

The Intelligence Imaging Lab (i2Lab) at Purdue University, West Lafayette, has a postdoctoral researcher position in computational photography. The candidate will work closely with Professor Stanley Chan to develop next generation optical and algorithmic techniques for imaging in adverse environments.

Qualification required: Ph.D. in electrical engineering, computer science, physics, or related fields, with a strong background in image processing, computer vision, and optics.

Prospective candidates shall send a CV and one representative paper to Prof Chan (stanchan@purdue.edu).

Graduate Research Assistant(s): (2021-2022)

We have multiple RA openings in computational photography:

  • Photon-limited imaging

  • Imaging through turbulence

Qualification required: B.S. in electrical engineering, computer science, physics, or related fields. Interested in computational photography. Has a good learning attitute.

Prospective students shall send a CV to Prof Chan (stanchan@purdue.edu).

Research News

2021-08 New paper ‘‘Photon-Limited Object Detection using Non-local Feature Matching and Knowledge Distillation’’, IEEE Intl. Conf. on Computer Vision Workshop (ICCV-w), 2021.
2021-08 New paper ‘‘Detecting and Segmenting Adversarial Graphics Patterns from Images’’, IEEE Intl. Conf. on Computer Vision Workshop (ICCV-w), 2021.
2021-08 New paper ‘‘Optical Adversarial Attack’’, IEEE Intl. Conf. on Computer Vision Workshop (ICCV-w), 2021.
2021-07 New paper ‘‘Accelerating Atmospheric Turbulence Simulation via Learned Phase-to-Space Transform’’, IEEE International Conference on Computer Vision (ICCV), 2021.
2021-06 Prof Chan gave an invited talk at CVPR 2021 on Imaging through Atmospheric Turbulence.
2021-03 New paper ‘‘Student-Teacher Learning from Clean Inputs to Noisy Inputs’’ IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
2020-11 New paper ‘‘HDR Imaging with Quanta Image Sensors: Theoretical Limits and Optimal Reconstruction’’ IEEE Transactions on Computational Imaging, 2020.
2020-08 Our project on turbulence receives a regular grant from NSF ECCS core.
2020-07 New paper ‘‘Dynamic low-light imaging with Quanta Image Sensors’’ European Conference on Computer Vision (ECCV), 2020.
2020-07 New paper ‘‘Image classification in the dark using Quanta Image Sensors’’ European Conference on Computer Vision (ECCV), 2020.
2020-07 New paper ‘‘Simulating anisoplanatic turbulence by sampling inter-modal and spatially correlated Zernike coefficients’’ Optical Engineering, 2020.
2020-06 New paper ‘‘One size fits all: Can we train one denoiser for all noise levels?’’ International Conference on Machine Learning (ICML), 2020.
2020-05 New paper ‘‘Simulating anisoplanatic turbulence by sampling correlated Zernike coefficients IEEE Intl. Conf. Computational Photography (ICCP), 2020.
2020-04 New research grant from the Army Research Office for funding our project on adversarial robustness in real environment.
2019-08 We receive a seed grant from Purdue College of Engineering on robust machine learning in real physical environment.
2017-07 One of our papers is picked by ACM Computing Reviews as the 21st Annual Best of Computing Notable Books and Articles.
2017-07 Our project on Quanta Image Sensors receives a regular grant from NSF CIF core.
2017-05 Our Images From Bits paper is selected as the front cover of MDPI Sensors Special Issue on Photon Counting Sensors.

News of i2Lab Faculty

2021-08 Prof Chan is recognized by the IEEE Signal Processing Society as an Outstanding Associate Editor for the IEEE Transactions on Computational Imaging.
2021-08 Prof Chan is recognized as an Outstanding engineering teacher.
2021-05 Prof Chan is promoted to Elmore Associate Professor of Electrical and Computer Engineering.
2020-04 Prof Chan is promoted to Associate Professor with tenure.
2019-06 Prof Chan receives Ruth and Joel Spira Outstanding Teaching Award 2019.
2019-03 Prof Chan receives Purdue College of Engineering Early Career Teaching Award 2019.
2019-01 Prof Chan is appointed as Associate Editor for IEEE Transactions on Computational Imaging.
2018-04 Prof Chan is selected as a Purdue Teaching for Tomorrow Fellow 2018.
2018-04 Prof Chan receives HKN Outstanding Professor Award 2018.
2017-03 Prof Chan is elevated to IEEE senior member.
2016-11 Prof Chan receives Purdue College of Engineering Outstanding Graduate Mentor Award.
2016-09 Prof Chan and PhD student Omar Elgendy wins Best Paper Award in IEEE ICIP 2016.
2016-09 Prof Chan is appointed as an Associate Editor for Optics Express.
2016-09 Prof Chan and undergraduate students appear in IEEE Signal Processing Magazine for SP Cup 2016.
2016-05 Prof Chan co-organizes a special session on Integration of Imaging Systems and Computational Algorithms in ICIP 2016.
2016-03 Prof Chan and undergraduate students win IEEE Signal Processing Cup 2016 Second Prize.
2015-11 Prof Chan receives HKN Outstanding Teacher Award 2015.
2015-09 Prof Chan is elected to IEEE Signal Processing Society Special Interest Group on Computational Imaging.

News of i2Lab Members

2020-04 Guanzhe Hong received Magoon Excellence TA Award 2020.
2019-07 Xiran Wang for passing his Ph.D. defense. Congratulations Dr. Wang!
2019-05 Omar Elgendy for passing his Ph.D. defense. Congratulations Dr. Elgendy!
2018-05 Joon Hee Choi for passing his Ph.D. defense. Congratulations Dr. Choi!
2018-01 Omar Elgendy for winning the Purdue Bilsland Dissertation Fellowship.
2017-12 Xiran Wang and Omar Elgendy for passing their preliminary exam.

Education News

2021-06 Summer course on Machine Learning for Beginners. Registration open!
2020-11 New book on Introduction to Probability for Data Science.
2020-08 ECE302 Undergraduate Probability Fall 2020. See course Lectures and Videos.
2021-01 ECE595 Machine Learning I Spring 2021. See course Lectures and Videos.

Media Coverage

2021-08 Optical adversarial attack can change the meaning of road signs (unite.ai).
2020-11 New HDR imaging capability using single-photon image sensors (Purdue ECE News).
2020-07 New breakthroughs in computer vision for imaging in the dark (Purdue ECE News).
2020-07 Resolving fast movement in low light (Image Sensor World Blog).
2020-06 Training one deep neural network for all noise levels (Purdue ECE News).
2020-05 ECE researcher to study adversarial attack in real environment (Purdue ECE News).

Recent Publications

‘‘Photon-Limited Object Detection using Non-local Feature Matching and Knowledge Distillation’’, IEEE Intl. Conf. on Computer Vision Workshop (ICCV-w), 2021.
‘‘Detecting and Segmenting Adversarial Graphics Patterns from Images’’, IEEE Intl. Conf. on Computer Vision Workshop (ICCV-w), 2021.
‘‘Optical Adversarial Attack’’, IEEE Intl. Conf. on Computer Vision Workshop (ICCV-w), 2021.
‘‘Accelerating Atmospheric Turbulence Simulation via Learned Phase-to-Space Transform’’, IEEE International Conference on Computer Vision (ICCV), 2021.
‘‘Student-Teacher Learning from Clean Inputs to Noisy Inputs’’, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
‘‘HDR Imaging with Quanta Image Sensors: Theoretical Limits and Optimal Reconstruction’’, IEEE Trans. Computational Imaging, 2020.
‘‘Dynamic low-light imaging with Quanta Image Sensors’’, European Conference on Computer Vision (ECCV), 2020.
‘‘Image classification in the dark using Quanta Image Sensors’’, European Conference on Computer Vision (ECCV), 2020.
‘‘Simulating anisoplanatic turbulence by sampling inter-modal and spatially correlated Zernike coefficients’’, Optical Engineering, 2020.
‘‘One size fits all: Can we train one denoiser for all noise levels?’’, accepted to International Conference on Machine Learning (ICML), 2020. (Video)
‘‘Simulating anisoplanatic turbulence by sampling correlated Zernike coefficients’’, IEEE International Conference on Computational Photography (ICCP), 2020. (Video)
‘‘Automatic foreground extraction from imperfect backgrounds using multi-agent consensus equilibrium’’, submitted, 2019.
‘‘Color filter arrays for Quanta Image Sensors’’, IEEE Trans. Computational Imaging, vol. 6, pp. 652-665, Jan. 2020.
‘‘Plug-and-Play methods for magnetic resonance imaging’’, IEEE Signal Processing Magazine, vol. 37, no. 1, 105-116, Jan. 2020.

Sponsors

Research at i2Lab is sponsored by

  • Up-coming grant from IARPA.

  • Up-coming grant from NSF.

  • NSF: SCALE MoDL: Robust Deep Learning in Real Physical Space: Generalization, Scalability, and Credibility (2021-2024) (co-PI)

  • NSF: CCSS: Small: Short-Exposure Imaging through Atmospheric Turbulence using Single Photon Image Sensors (2020-2023) (single PI)

  • Army Research Office: Adversarial Robustness in Real Environment (2020-2021) (single PI)

  • NSF: CIF: Medium: Multi-Agent Consensus Equilibrium: Modular Methods for Integrating Disparate Sources of Expertise (2018-2022) (co-PI)

  • NSF: CIF: Small: Signal Processing for Quanta Image Sensors: Reconstruction, Sampling, and Applications (2017-2021) (single PI)

  • Air Force Research Lab and Leidos: Mitigating Turbulence in Long Range Imagery using Consensus Equilibrium (2018 - 2019) (single PI)

  • HypeVR: Image Processing for Virtual Reality Applications (2017-2018) (single PI)

  • and other sponsors.