Saved in:
Bibliographic Details
Main Authors: Tran, Nhat Thanh, Bui, Kevin, Xin, Jack
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.13400
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912833909817344
author Tran, Nhat Thanh
Bui, Kevin
Xin, Jack
author_facet Tran, Nhat Thanh
Bui, Kevin
Xin, Jack
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_13400
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Deep Image Prior with L0 Gradient Regularizer for Image Smoothing
Tran, Nhat Thanh
Bui, Kevin
Xin, Jack
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title Deep Image Prior with L0 Gradient Regularizer for Image Smoothing
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2601.13400