IEEE Trans. on Computational Imaging

Hello computational imaging friends and researchers 👋Follow this account for updates on newly published Trans. on Computational Imaging papers and news!

📣 "A Convergent Generalized Krylov Subspace Method for CS MRI Reconstruction with Gradient-Driven Denoisers" now on Early Access! ieeexplore.ieee.org/document/11358… 🗞️Reconst. with gradient-driven denoisers, achieving nonconvex convergence and fast reconst. for non-Cartesian acquisitions

📣📣"Scan-Adaptive MRI Undersampling Using Neighbor-based Optimization (SUNO)"by @sidgautam95,@MRInicole et al. Now on Early Access! ieeexplore.ieee.org/document/11346… 🗞️A scan-adaptive MRI undersampling framework that selects optimized Cartesian masks per scan, outperforming fixed sampling

📣📣"Convergent Complex Quasi-Newton Proximal Methods for Gradient-Driven Denoisers in CS MRI Reconst"ieeexplore.ieee.org/document/11216… 🗞️A complex quasi-Newton proximal method for CS MRI reconst. that integrates gradient-driven denoisers with a Hermitian positive-definite Hessian estimate

📣📣"Using Randomized Nyström Preconditioners to Accelerate Variational Image Reconstruction" ieeexplore.ieee.org/document/11208… A method to compute/apply a randomized Nyström-based preconditioner on-the-fly using forward/adjoint operators, accelerating large-scale variational image reconst

📣📣 "Limitations of Data-Driven Spectral Reconstruction: An Optics-Aware Analysis" by @__QiangFu__ @EunsueChoi @SuhyunShin9812 @SeungHwanBaek8 et al. Now on Early Access! ieeexplore.ieee.org/document/11206… 🗞️ How metamerism and limited dataset diversity constrain RGB-to-spectral reconst.

🗞️Looking to accelerate compressed sensing MRI reconstruction? Check out "Provable Preconditioned Plug-and-Play Approach for Compressed Sensing MRI Reconstruction", which introduces a provable plug-and-play framework to achieve faster reconstruction. ieeexplore.ieee.org/document/10711…

📣📣"Fourier Analysis of Interference Scanning Optical Probe Microscopy" by @EmmanuelSoubies et al. ieeexplore.ieee.org/document/11143… A Fourier analysis of Interf. Scanning Optical probe Microscopy (ISOM), offering new insights into this modality operating in the intermediate-field regime

📣📣"DAMMER: Direct Adaptive Multi-Resolution MEsh Reconstruction From X-Ray Measurements" by @imec_visionlab ieeexplore.ieee.org/document/11074… DAMMER adaptively reconstructs attenuation values on a progressively optimized triangle mesh, diminishing partial volume effects. @FWOVlaanderen

📣📣"Swap-Net: A Memory-Efficient 2.5D Network for Sparse-View 3D Cone Beam CT Reconstruction to ICF Applications"by @Xiaojian_Xu, @JasonHu07825282 et al: ieeexplore.ieee.org/document/11011… 3D image reconst. using 2D convolutions with novel axis-swapping operations, avoiding volume slicing.

📣📣"Laser Protection via Jointly Learned Defocus and Image Reconstruction" by @jojomey87 et al. at @FraunhoferIOSB: ieeexplore.ieee.org/document/11074… A novel method protects optical sensors from laser damage by defocusing the imaging system and using an optimized CA and ML reconstruction.

🎉 Exciting News from the IEEE TCI! 📈 We are thrilled to announce that our journal's Impact Factor has increased to 4.8, as published in the 2025 Journal Citation Reports by Clarivate!. 🙏 A heartfelt thank you to our global community of contributors and readers. #ThankYou

🚀 Stay updated with the latest in computational imaging! Follow us on LinkedIn for news, paper highlights, and updates from IEEE Transactions on Computational Imaging. 🔗 Connect here: linkedin.com/company/ieee-t… #ComputationalImaging #IEEE #TCI #Research

📢📢Multi-layered Surface Estimation for Low-cost Optical Coherence Tomography If you're curious how you can implement a low-cost optical coherence tomography system don't miss this paper by J. Rapp et al. from @merl_news Now on early access: ieeexplore.ieee.org/document/10752…

📽️📽️ New spotlight video for "PRNet: Pyramid Restoration Network for RAW Image Super-Resolution" by Ling et al. Check it out on our channel: youtu.be/nMD2YDwqN-Y Paper: ieeexplore.ieee.org/document/10463…

📢📢 Want to learn more about the @IEEE_TCI paper "A Complex Quasi-Newton Proximal Method for Image Reconstruction in Compressed Sensing MRI" by Hong, Hernandez-Garcia, and Fessler from @UMichCSE? Check out the spotlight! youtu.be/1koOC6YHRTo Paper: ieeexplore.ieee.org/document/10444…

Inverse Problems: Discrete or Continuous? @MehrsaPourya et al. from @big_epfl explain that box splines and multi-res bridge the gap: "A Box-Spline Framework for Inverse Problems with Continuous-Domain Sparsity Constraints” On early access: ieeexplore.ieee.org/document/10533…

Got highly compressed and noisy radar data? Plug-and-Play Regularization on Magnitude with Deep Priors for 3D Near-Field MIMO Imaging by Oral (@okyanus_oral) and Oktem from the Middle East Technical University (@metu_eee) ieeexplore.ieee.org/document/10517…

📣📣 "Local monotone operator learning using non-monotone operators: MnM-MOL", by M. John, J.R. Chand, and M. Jacob from @UIowaEngr now on early access! ieeexplore.ieee.org/document/10510… For a sneak peek, watch this spotlight presentation: youtu.be/E9NedZY-EeU

@stanley_h_chan Want to learn a little more? Here's the spotlight video on @IEEE_TCI's YouTube channel! youtu.be/hMBKJxjk3ZU

📢 New paper accepted to @IEEE_TCI! The Secrets of Non-Blind Poisson Deconvolution arxiv.org/abs/2309.03105 Five secrets: Use Wiener filter Use iterations Do things in feature space Poisson likelihood not needed Learn hyperparameters

If you want to learn the best kept secrets of non-blind Poisson deconvolution, check out our newest spotlight video: youtu.be/hMBKJxjk3ZU 🤫🤫 Paper: ieeexplore.ieee.org/document/10449… by Gnanasambandam, Sanghvi and @stanley_h_chan from @PurdueECE.