computer-vision-2

JPEG Artifact Removal

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in jpeg-artifact-removal-5

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find jpeg-artifact-removal-5 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Projected Distribution Loss for Image Enhancement

Hossein Talebi, P. Milanfar, M. Delbracio•Tue Dec 15 2020

It is demonstrated that aggregating 1D-Wasserstein distances between CNN activations is more reliable than the existing approaches, and it can significantly improve the perceptual performance of enhancement models.

40

Content

0

Paper Graph

Towards Flexible Blind JPEG Artifacts Removal

K. Zhang, Radu Timofte, Jiaxi Jiang•Tue Sep 28 2021

This paper proposes a flexible blind convolutional neural network that can predict the adjustable quality factor to control the trade-off between artifacts removal and details preservation and achieves favorable performance against state-of-the-art methods in terms of both quantitative metrics and visual quality.

136 0

Paper Graph

Restoring Images with Unknown Degradation Factors by Recurrent Use of a Multi-branch Network

Xing Liu, M. Suganuma, Xiyang Luo, Takayuki Okatani•Tue Jul 09 2019

This paper designs a network having multiple pairs of input and output branches and uses it in a recurrent fashion such that a different branch pair is used at each of the recurrent paths and proposes a two-step training method for the network, which consists of multi-task learning and finetuning.

9 0

Paper Graph

Are Deep Neural Architectures Losing Information? Invertibility Is Indispensable

Tom Gedeon, Saeed Anwar, Zhenyue Qin, Yang Liu, Sabrina Caldwell•Sun Sep 06 2020

This work proves that a deep neural architecture can preserve maximum details about the given data if and only if the architecture is invertible, and shows that IRAE consistently outperforms non-invertible ones.

19 0

Paper Graph

Hypernetwork-Based Adaptive Image Restoration

Shai Aharon, Gil Ben-Artzi•Sun Jun 12 2022

This work presents an approach that is highly accurate and allows a significant reduction in the number of parameters, in contrast to existing methods, that can restore images using a single fixed-size model, regardless of the number of degradation levels.

9 0

Paper Graph

DriftRec: Adapting Diffusion Models to Blind JPEG Restoration

Simon Welker, Timo Gerkmann, H. Chapman•Fri Nov 11 2022

This work proposes an elegant modification of the forward stochastic differential equation of diffusion models to adapt them to solve blind JPEG restoration at high compression levels and names it DriftRec, and shows that it can escape the tendency of other methods to generate blurry images, and recovers the distribution of clean images significantly more faithfully.

25 0

Paper Graph

Restore Anything Pipeline: Segment Anything Meets Image Restoration

Jiaxi Jiang, Christian Holz•Sun May 21 2023

The Restore Anything Pipeline (RAP), a novel interactive and per-object level image restoration approach that incorporates a controllable model to generate different results that users may choose from, is introduced.

11 0

Paper Graph

Removing Image Artifacts From Scratched Lens Protectors

B. Wen, A. Kot, Wenhan Yang, Renjie Wan, Yufei Wang, Lap-Pui Chau•Fri Feb 10 2023

This work considers the inherent challenges in a unified framework with two cooperative modules, which facilitate the performance boost of each other, and demonstrates that the method outperforms the baselines qualitatively and quantitatively.

3 0

Paper Graph

Bidirectional Consistency Models

Liangchen Li, Jiajun He•Mon Mar 25 2024

Bidirectional Consistency Model (BCM) is introduced, which learns a single neural network that enables both forward and backward traversal along the PF ODE, efficiently unifying generation and inversion tasks within one framework.

18 0

Paper Graph

Controlling Vision-Language Models for Multi-Task Image Restoration

Ziwei Luo, Fredrik K. Gustafsson, Jens Sjolund, Zheng Zhao, Thomas B. Schon•Sun Oct 01 2023

This paper presents a degradation-aware vision-language model (DA-CLIP) to better transfer pretrained vision-language models to low-level vision tasks as a multi-task framework for image restoration.

83 0

Paper Graph

Adding a benchmark result helps the community track progress.