Invertible generative models for inverse problems: mitigating representation error and dataset bias

• URL: http://arxiv.org/abs/1905.11672v5
• Date: Mon, 27 Oct 2025 02:35:51 GMT
• Title: Invertible generative models for inverse problems: mitigating representation error and dataset bias
• Authors: Muhammad Asim, Mara Daniels, Oscar Leong, Ali Ahmed, Paul Hand,
• Abstract summary: Trained generative models have shown remarkable performance as priors for inverse problems in imaging.<n>We demonstrate that invertible neural networks, which have zero representation error by design, can be effective natural signal priors at inverse problems.
• Score: 6.07645721775351
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Trained generative models have shown remarkable performance as priors for inverse problems in imaging -- for example, Generative Adversarial Network priors permit recovery of test images from 5-10x fewer measurements than sparsity priors. Unfortunately, these models may be unable to represent any particular image because of architectural choices, mode collapse, and bias in the training dataset. In this paper, we demonstrate that invertible neural networks, which have zero representation error by design, can be effective natural signal priors at inverse problems such as denoising, compressive sensing, and inpainting. Given a trained generative model, we study the empirical risk formulation of the desired inverse problem under a regularization that promotes high likelihood images, either directly by penalization or algorithmically by initialization. For compressive sensing, invertible priors can yield higher accuracy than sparsity priors across almost all undersampling ratios, and due to their lack of representation error, invertible priors can yield better reconstructions than GAN priors for images that have rare features of variation within the biased training set, including out-of-distribution natural images. We additionally compare performance for compressive sensing to unlearned methods, such as the deep decoder, and we establish theoretical bounds on expected recovery error in the case of a linear invertible model.

Related papers

• Solving Inverse Problems with FLAIR [68.87167940623318]
  We present FLAIR, a training-free variational framework that leverages flow-based generative models as prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization [11.393603788068777]
  In ill-posed imaging inverse problems, there can exist many hypotheses that fit both the observed measurements and prior knowledge of the true image. We propose a fast and accurate posterior-sampling conditional generative adversarial network (cGAN) that, through a novel form of regularization, aims for correctness in the posterior mean.
  arXiv  Detail & Related papers  (2024-11-01T14:09:28Z)
• Fast constrained sampling in pre-trained diffusion models [80.99262780028015]
  We propose an algorithm that enables fast, high-quality generation under arbitrary constraints.<n>Our approach produces results that rival or surpass the state-of-the-art training-free inference methods.
  arXiv  Detail & Related papers  (2024-10-24T14:52:38Z)
• Denoising Diffusion Restoration Models [110.1244240726802]
  Denoising Diffusion Restoration Models (DDRM) is an efficient, unsupervised posterior sampling method. We demonstrate DDRM's versatility on several image datasets for super-resolution, deblurring, inpainting, and colorization.
  arXiv  Detail & Related papers  (2022-01-27T20:19:07Z)
• Generative Flows as a General Purpose Solution for Inverse Problems [0.0]
  We propose a regularization term to directly produce high likelihood reconstructions. We evaluate our method in image denoising, image deblurring, image inpainting, and image colorization.
  arXiv  Detail & Related papers  (2021-10-25T21:56:44Z)
• Robust lEarned Shrinkage-Thresholding (REST): Robust unrolling for sparse recover [87.28082715343896]
  We consider deep neural networks for solving inverse problems that are robust to forward model mis-specifications. We design a new robust deep neural network architecture by applying algorithm unfolding techniques to a robust version of the underlying recovery problem. The proposed REST network is shown to outperform state-of-the-art model-based and data-driven algorithms in both compressive sensing and radar imaging problems.
  arXiv  Detail & Related papers  (2021-10-20T06:15:45Z)
• Inverse Problems Leveraging Pre-trained Contrastive Representations [88.70821497369785]
  We study a new family of inverse problems for recovering representations of corrupted data. We propose a supervised inversion method that uses a contrastive objective to obtain excellent representations for highly corrupted images. Our method outperforms end-to-end baselines even with a fraction of the labeled data in a wide range of forward operators.
  arXiv  Detail & Related papers  (2021-10-14T15:06:30Z)
• Low-Light Image Enhancement with Normalizing Flow [92.52290821418778]
  In this paper, we investigate to model this one-to-many relationship via a proposed normalizing flow model. An invertible network that takes the low-light images/features as the condition and learns to map the distribution of normally exposed images into a Gaussian distribution. The experimental results on the existing benchmark datasets show our method achieves better quantitative and qualitative results, obtaining better-exposed illumination, less noise and artifact, and richer colors.
  arXiv  Detail & Related papers  (2021-09-13T12:45:08Z)
• Deep Neural Networks are Surprisingly Reversible: A Baseline for Zero-Shot Inversion [90.65667807498086]
  This paper presents a zero-shot direct model inversion framework that recovers the input to the trained model given only the internal representation. We empirically show that modern classification models on ImageNet can, surprisingly, be inverted, allowing an approximate recovery of the original 224x224px images from a representation after more than 20 layers.
  arXiv  Detail & Related papers  (2021-07-13T18:01:43Z)
• Using Deep Image Priors to Generate Counterfactual Explanations [38.62513524757573]
  A deep image prior (DIP) can be used to obtain pre-images from latent representation encodings. We propose a novel regularization strategy based on an auxiliary loss estimator jointly trained with the predictor.
  arXiv  Detail & Related papers  (2020-10-22T20:40:44Z)
• Reducing the Representation Error of GAN Image Priors Using the Deep Decoder [16.580772758959245]
  We show a method for reducing the representation error of GAN priors by modeling images as the linear combination of a GAN prior and a Deep Decoder.<n>For compressive sensing and image superresolution, our hybrid model exhibits consistently higher PSNRs than both the GAN priors and Deep Decoder separately.
  arXiv  Detail & Related papers  (2020-01-23T18:37:24Z)

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.