Deep Image Prior with L0 Gradient Regularizer for Image Smoothing

• URL: http://arxiv.org/abs/2601.13400v1
• Date: Mon, 19 Jan 2026 21:10:32 GMT
• Title: Deep Image Prior with L0 Gradient Regularizer for Image Smoothing
• Authors: Nhat Thanh Tran, Kevin Bui, Jack Xin,
• Abstract summary: Image smoothing is a fundamental image processing operation that preserves the underlying structure, such as strong edges and contours, and removes minor details and textures in an image.<n>Many image smoothing algorithms rely on computing local window statistics or solving an optimization problem.<n>Recent state-of-the-art methods leverage deep gradient training, but they require a carefully curated training.<n>This framework can perform high-quality image smoothing without any data.
• Score: 2.0901018134712297
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Image smoothing is a fundamental image processing operation that preserves the underlying structure, such as strong edges and contours, and removes minor details and textures in an image. Many image smoothing algorithms rely on computing local window statistics or solving an optimization problem. Recent state-of-the-art methods leverage deep learning, but they require a carefully curated training dataset. Because constructing a proper training dataset for image smoothing is challenging, we propose DIP-$\ell_0$, a deep image prior framework that incorporates the $\ell_0$ gradient regularizer. This framework can perform high-quality image smoothing without any training data. To properly minimize the associated loss function that has the nonconvex, nonsmooth $\ell_0$ ``norm", we develop an alternating direction method of multipliers algorithm that utilizes an off-the-shelf $\ell_0$ gradient minimization solver. Numerical experiments demonstrate that the proposed DIP-$\ell_0$ outperforms many image smoothing algorithms in edge-preserving image smoothing and JPEG artifact removal.

Related papers

• Locally Orderless Images for Optimization in Differentiable Rendering [80.09571356394574]
  We introduce a method that uses locally orderless images, where each pixel maps to a histogram of intensities that preserves local variations in appearance.<n>We validate our method on various inverse problems using both synthetic and real data.
  arXiv  Detail & Related papers  (2025-03-27T19:17:58Z)
• An Improved Optimal Proximal Gradient Algorithm for Non-Blind Image Deblurring [15.645711819668582]
  We introduce an improved optimal proximal gradient algorithm (IOptISTA) to efficiently address the non-blind image deblurring problem.<n>The results indicate that our algorithm yields enhanced PSNR and SSIM values, as well as a reduced tolerance, compared to existing methods.
  arXiv  Detail & Related papers  (2025-02-11T14:52:11Z)
• Learning of Patch-Based Smooth-Plus-Sparse Models for Image Reconstruction [14.93489065234423]
  We formulate the optimization as a bilevel problem.<n>We evaluate our method for denoising, super-resolution, and compressed-sensing magnetic-resonance imaging.
  arXiv  Detail & Related papers  (2024-12-17T16:34:32Z)
• Euler's Elastica Based Cartoon-Smooth-Texture Image Decomposition [4.829677240798159]
  We propose a novel model for decomposing grayscale images into three distinct components.<n>The structural part represents strong boundaries and regions with strong light-to-dark transitions; the smooth part, capturing soft shadows and shadows; and the oscillatory, characterizing textures and noise.
  arXiv  Detail & Related papers  (2024-07-03T03:42:33Z)
• Image-GS: Content-Adaptive Image Representation via 2D Gaussians [52.598772767324036]
  We introduce Image-GS, a content-adaptive image representation based on 2D Gaussians radiance.<n>It supports hardware-friendly rapid access for real-time usage, requiring only 0.3K MACs to decode a pixel.<n>We demonstrate its versatility with several applications, including texture compression, semantics-aware compression, and joint image compression and restoration.
  arXiv  Detail & Related papers  (2024-07-02T00:45:21Z)
• Deep Richardson-Lucy Deconvolution for Low-Light Image Deblurring [48.80983873199214]
  We develop a data-driven approach to model the saturated pixels by a learned latent map. Based on the new model, the non-blind deblurring task can be formulated into a maximum a posterior (MAP) problem. To estimate high-quality deblurred images without amplified artifacts, we develop a prior estimation network.
  arXiv  Detail & Related papers  (2023-08-10T12:53:30Z)
• Optimizing CT Scan Geometries With and Without Gradients [7.788823739816626]
  We show that gradient-based optimization algorithms are a possible alternative to gradient-free algorithms. gradient-based algorithms converge substantially faster while being comparable to gradient-free algorithms in terms of capture range and robustness to the number of free parameters.
  arXiv  Detail & Related papers  (2023-02-13T10:44:41Z)
• Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization [59.19214040221055]
  We propose a novel spatial-separated curve rendering network (S$2$CRNet) for efficient and high-resolution image harmonization. The proposed method reduces more than 90% parameters compared with previous methods. Our method can work smoothly on higher resolution images in real-time which is more than 10$times$ faster than the existing methods.
  arXiv  Detail & Related papers  (2021-09-13T07:20:16Z)
• Efficient and Differentiable Shadow Computation for Inverse Problems [64.70468076488419]
  Differentiable geometric computation has received increasing interest for image-based inverse problems. We propose an efficient yet efficient approach for differentiable visibility and soft shadow computation. As our formulation is differentiable, it can be used to solve inverse problems such as texture, illumination, rigid pose, and deformation recovery from images.
  arXiv  Detail & Related papers  (2021-04-01T09:29:05Z)
• A deep primal-dual proximal network for image restoration [8.797434238081372]
  We design a deep network, named DeepPDNet, built from primal-dual iterations associated with the minimization of a standard penalized likelihood with an analysis prior. Two different learning strategies: "Full learning" and "Partial learning" are proposed, the first one is the most efficient numerically. Extensive results show that the proposed DeepPDNet demonstrates excellent performance on the MNIST and the more complex BSD68, BSD100, and SET14 datasets for image restoration and single image super-resolution task.
  arXiv  Detail & Related papers  (2020-07-02T08:29:52Z)
• The Power of Triply Complementary Priors for Image Compressive Sensing [89.14144796591685]
  We propose a joint low-rank deep (LRD) image model, which contains a pair of complementaryly trip priors. We then propose a novel hybrid plug-and-play framework based on the LRD model for image CS. To make the optimization tractable, a simple yet effective algorithm is proposed to solve the proposed H-based image CS problem.
  arXiv  Detail & Related papers  (2020-05-16T08:17:44Z)

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.