Journal-first (JIST/JPI) Submissions

∙ Journal-first (JIST/JPI) Submissions Due 31 July
∙ Final Journal-first manuscripts due 31 Oct
Conference Papers Submissions
∙ Extended Submission Deadline
∙ FastTrack Proceedings Manuscripts Due 21 Dec 
∙ All Outstanding Manuscripts Due 15 Feb 2024
Registration Opens mid-Oct
Demonstration Applications Due 18 Dec
Early Registration Ends 18 Dec

Hotel Reservation Deadline 3 Jan
Symposium Begins
21 Jan
Non-FastTrack Proceedings Manuscripts Due
15 Feb

Computational Imaging XXII

Conference keywords: inverse problems, image reconstruction, image analysis, denoising, model-based imaging

On this page


Conference Overview

More than ever before, computers and computation are critical to the image formation process. Across diverse applications and fields, remarkably similar imaging problems appear, requiring sophisticated mathematical, statistical, and algorithmic tools. This conference focuses on imaging as a marriage of computation with physical devices. It emphasizes the interplay between mathematical theory, physical models, and computational algorithms that enable effective current and future imaging systems. Contributions to the conference are solicited on topics ranging from fundamental theoretical advances to detailed system-level implementations and case studies.

2024 Conference Topics

Algorithms and methodologies

  • Inverse methods
  • Model-based imaging and compressed sensing
  • Estimation techniques
  • Imaging system modeling and simulation
  • Optimization approaches
  • Multiscale image processing and modeling
  • Statistical learning and analysis methods

Key problem areas

  • Image recovery from sensor data
  • Tomography, transmission, and emission
  • Denoising, demosaicing, color correction
  • Deblurring and super-resolution rendering
  • Commercial and industrial imaging
  • Radar and LIDAR imaging
  • Synthetic aperture radar
  • Holographic and coherent optical imaging
  • Coded aperture and compressed sensing
  • MRI, anatomical, functional, and molecular
  • Visual perception as an inverse problem
  • Microscopy, light, EM, and non-classical
  • Optical coherence imaging
  • Acoustic imaging
  • Diffusion optical imaging
  • Electrical resistance and impedance imaging
  • Crystallography
  • Computational depth-of-field enhancement
  • Plenoptics and non-classical image capture

Current and future applications

  • Scientific imaging for material science
  • Consumer imaging and computational photography
  • Super-resolution and enhancement
  • Imaging and camera networks
  • Non-destructive evaluation for additive manufacturing
  • Medical imaging and image-guided surgery
  • Microscopy and clinical applications
  • Emerging biomedical applications
  • Geophysical imaging
  • Materials imaging and characterization
  • Nondestructive testing and evaluation
  • Imagery-based surveillance and tracking
  • Target classification and identification
  • Remote sensing applications

2024 Special Sessions

Additive Manufacturing: In- and Ex-situ Imaging for Monitoring and Non-destructive Characterization

Session Organizing Chairs:
Amir Ziabari, Oak Ridge National Laboratory (US)
Singanallur Venkatakrishnan, Oak Ridge National Laboratory (US)
Mehrnaz Salarian, Divergent Technologies, Inc. (US)
Alirza Sarraf, Divergent Technologies, Inc. (US)

Additive Manufacturing technologies offer unparalleled flexibility in fabricating complex geometries and customized components. However, challenges related to part quality, performance, and certification hinder widespread industrial adoption. To address these challenges, there is a pressing need for innovative approaches that integrate modeling and simulation, in-situ monitoring, and ex-situ characterization.

This special session aims to bring together experts with cross cutting research background in Materials Science, Computational imaging, Computer Vision, Machine Learning and Additive Manufacturing to explore the possibilities and advancements in this emerging field. We encourage abstract submissions on the following topics, but not limited to:

  • In-situ imaging and sensing methods and for real-time monitoring of AM processes
  • Ex-situ imaging techniques for comprehensive characterization of AM parts and materials
  • Novel approaches for non-destructive evaluation and quality assessment in AM
  • Image analysis and processing algorithms for AM monitoring and characterization
  • Multimodal imaging approaches and their application in AM research

Generative Artificial Intelligence for Remote Sensing

Session Organizing Chair:
Andre van Rynbach , Air Force Research Laboratory (US)

Recent advances in applications at the intersection of computational imaging, computer vision, and remote sensing have accompanied a surge in interest surrounding generative artificial intelligence capabilities. The emergence of generative adversarial networks (GANs), variational autoencoders, and neural radiance fields (NeRFs) has led to promising advances in a range of applications, including synthetic data generation, 3D novel view synthesis, texture mapping, super resolution, panchromatic sharpening, data augmentation, haze and cloud removal, generative diffusion models, and image segmentation, among others. In this special session, recent developments with generative AI for remote sensing and computer vision will be highlighted along with the exciting implications for computational imaging.

Implicit Neural Representations for Inverse Imaging

Session Organizing Chairs:
K. Aditya Mohan, Lawrence Livermore National Laboratory (US)
Hyojin Kim, Lawrence Livermore National Laboratory (US)

Implicit neural representation (INR) networks have been used to solve a wide variety of inverse problems. INRs are function approximators that predict the reconstruction value as a function of the continuous coordinates (space, time, etc.). The inductive bias of an INR is useful as a prior modeling constraint to mitigate the ill-posed nature of an inverse problem. Importantly, INR is a scalable unsupervised approach to reconstruction by inverting a forward model for the image formation process. This session features research that uses INRs in a variety of inverse imaging applications, and showcases their flexibility and usefulness.

Imaging at the Edge

Session Organizing Chair:
Mel White, Rice University (US)

As cameras get smaller and more ubiquitous, the sensors they employ must do more than light detection. Edge computing devices for imaging perform computation at the sensor—through on-chip digital electronics, analog processing of the transduced signal, manipulation of the light field, or a combination of these. By considering the sensing hardware as part of the computational pipeline, such devices show promise for overcoming challenges in bandwidth, speed, and size. This session showcases a few examples, and consider the current and future application spaces for edge computing image sensors.

The Intersection of Computational Imaging and Materials Science

Session Organizing Chairs:
Jeff P. Simmons, Air Force Research Laboratory (US)
Yuejie Chi, Carnegie Mellon University (US)
B. Reeja Jayan, Carnegie Mellon University (US)

Advances in machine learning echo through the halls of traditional fields, changing the very way we view these subjects. Yet the enigmatic complexity of materials science sets it apart, demanding multi-scale observations of hierarchical structure with a myriad of microscopic techniques. Yet, within the shadows, the spirit of machine learning lurks, and computational imaging techniques, such as advanced microscopy, tomography, and spectroscopy, are seen in a new light, allowing unprecedented advances, transcending the boundaries of the unknown. Efficient extraction of complex structural and chemical information from materials at various scales and fusion of high-dimensional imaging datasets enables the automatic identification of key material features, leading to accelerated material discovery and characterization. An apparition of possibilities emerges enabling the prediction of material behavior, degradation, and performance under different conditions for designing innovative materials for applications in energy, electronics, medicine, and beyond. The committee invites contributions exploring the advancements in data acquisition, image reconstruction, and feature extraction techniques. Additionally, the organizing chairs encourage presentations on applying deep neural networks, generative models, graph theory and topology, optimization methods, inverse methods, physics integration with learning, and other emerging techniques toward enhancing materials analysis and accelerating the translation of research findings into real-world applications.

This is a joint special session with Machine Learning for Scientific Imaging 2024.

2024 Committee

Conference Chairs

Charles A. Bouman, Purdue University (US)
Gregery T. Buzzard, Purdue University (US)

Program Committee

Begum Gulsoy, Northwestern University (US)
Clem Karl, Boston University (US)
Eric Miller, Tufts University (US)
Joseph A O'Sullivan, Washington University in St. Louis (US)
Emma Reid, Oak Ridge National Laboratory (US)
Hector J Santos-Villalobos, Oak Ridge National Laboratory (US)
Ken D. Sauer, University of Notre Dame (US)

No content found

No content found

No content found