Image Reconstruction via Deep Image Prior Subspaces

• URL: http://arxiv.org/abs/2302.10279v2
• Date: Mon, 5 Jun 2023 09:50:48 GMT
• Title: Image Reconstruction via Deep Image Prior Subspaces
• Authors: Riccardo Barbano, Javier Antor\'an, Johannes Leuschner, Jos\'e Miguel Hern\'andez-Lobato, Bangti Jin, \v{Z}eljko Kereta
• Abstract summary: Deep learning has been widely used for solving image reconstruction tasks but its deployability has been held back due to the shortage of high-quality training data. We present a novel approach to tackle these issues by restricting DIP optimisation to a sparse linear subspace of its parameters. The low-dimensionality of the subspace reduces DIP's tendency to fit noise and allows the use of stable second order optimisation methods.
• Score: 0.18472148461613155
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning has been widely used for solving image reconstruction tasks but its deployability has been held back due to the shortage of high-quality training data. Unsupervised learning methods, such as the deep image prior (DIP), naturally fill this gap, but bring a host of new issues: the susceptibility to overfitting due to a lack of robust early stopping strategies and unstable convergence. We present a novel approach to tackle these issues by restricting DIP optimisation to a sparse linear subspace of its parameters, employing a synergy of dimensionality reduction techniques and second order optimisation methods. The low-dimensionality of the subspace reduces DIP's tendency to fit noise and allows the use of stable second order optimisation methods, e.g., natural gradient descent or L-BFGS. Experiments across both image restoration and tomographic tasks of different geometry and ill-posedness show that second order optimisation within a low-dimensional subspace is favourable in terms of optimisation stability to reconstruction fidelity trade-off.

Related papers

• Towards Cross-View-Consistent Self-Supervised Surround Depth Estimation [9.569646683579899]
  Self-Supervised Surround Depth Estimation from consecutive images offers an economical alternative. Previous SSSDE methods have proposed different mechanisms to fuse information across images, but few of them explicitly consider the cross-view constraints. This paper proposes an efficient and consistent pose estimation design and two loss functions to enhance cross-view consistency for SSSDE.
  arXiv  Detail & Related papers  (2024-07-04T16:29:05Z)
• Double Duality: Variational Primal-Dual Policy Optimization for Constrained Reinforcement Learning [132.7040981721302]
  We study the Constrained Convex Decision Process (MDP), where the goal is to minimize a convex functional of the visitation measure. Design algorithms for a constrained convex MDP faces several challenges, including handling the large state space.
  arXiv  Detail & Related papers  (2024-02-16T16:35:18Z)
• Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging [17.511583657111792]
  Snapshot spectral imaging reconstruction aims to reconstruct three-dimensional spatial-spectral images from a single-shot two-dimensional compressed measurement. We introduce a generative model, namely the latent diffusion model (LDM), to generate degradation-free prior to deep unfolding method.
  arXiv  Detail & Related papers  (2023-11-24T04:55:20Z)
• Improving Neural Indoor Surface Reconstruction with Mask-Guided Adaptive Consistency Constraints [0.6749750044497732]
  We propose a two-stage training process, decouple view-dependent and view-independent colors, and leverage two novel consistency constraints to enhance detail reconstruction performance without requiring extra priors. Experiments on synthetic and real-world datasets show the capability of reducing the interference from prior estimation errors.
  arXiv  Detail & Related papers  (2023-09-18T13:05:23Z)
• Rank-Enhanced Low-Dimensional Convolution Set for Hyperspectral Image Denoising [50.039949798156826]
  This paper tackles the challenging problem of hyperspectral (HS) image denoising. We propose rank-enhanced low-dimensional convolution set (Re-ConvSet) We then incorporate Re-ConvSet into the widely-used U-Net architecture to construct an HS image denoising method.
  arXiv  Detail & Related papers  (2022-07-09T13:35:12Z)
• A Fast Alternating Minimization Algorithm for Coded Aperture Snapshot Spectral Imaging Based on Sparsity and Deep Image Priors [8.890754092562918]
  Coded aperture snapshot spectral imaging (CASSI) is a technique used to reconstruct three-dimensional hyperspectral images (HSIs) This paper proposes a fast alternating minimization algorithm based on the sparsity and deep image priors (Fama-P) of natural images.
  arXiv  Detail & Related papers  (2022-06-12T03:29:14Z)
• A Probabilistic Deep Image Prior for Computational Tomography [0.19573380763700707]
  Existing deep-learning based tomographic image reconstruction methods do not provide accurate estimates of reconstruction uncertainty. We construct a Bayesian prior for tomographic reconstruction, which combines the classical total variation (TV) regulariser with the modern deep image prior (DIP) For the inference, we develop an approach based on the linearised Laplace method, which is scalable to high-dimensional settings.
  arXiv  Detail & Related papers  (2022-02-28T14:47:14Z)
• Implicit Subspace Prior Learning for Dual-Blind Face Restoration [66.67059961379923]
  A novel implicit subspace prior learning (ISPL) framework is proposed as a generic solution to dual-blind face restoration. Experimental results demonstrate significant perception-distortion improvement of ISPL against existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-10-12T08:04:24Z)
• Cogradient Descent for Bilinear Optimization [124.45816011848096]
  We introduce a Cogradient Descent algorithm (CoGD) to address the bilinear problem. We solve one variable by considering its coupling relationship with the other, leading to a synchronous gradient descent. Our algorithm is applied to solve problems with one variable under the sparsity constraint.
  arXiv  Detail & Related papers  (2020-06-16T13:41:54Z)
• Light Field Spatial Super-resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization [99.96632216070718]
  Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution. The high-dimensional spatiality characteristic and complex geometrical structure of LF images make the problem more challenging than traditional single-image SR. We propose a novel learning-based LF framework, in which each view of an LF image is first individually super-resolved.
  arXiv  Detail & Related papers  (2020-04-05T14:39:57Z)
• Structure-Preserving Super Resolution with Gradient Guidance [87.79271975960764]
  Structures matter in single image super resolution (SISR) Recent studies benefiting from generative adversarial network (GAN) have promoted the development of SISR. However, there are always undesired structural distortions in the recovered images.
  arXiv  Detail & Related papers  (2020-03-29T17:26:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.