Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

computer-vision-6

Defocus Blur Detection

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 defocus-blur-detection-6

Trend

Dataset

Best Model

Actions

CUHK

CTCUG

EBD

Libraries

Use these libraries to find defocus-blur-detection-6 models and implementations

Datasets

CUHK03

HistoArtifacts

EBD

Subtasks

No subtasks available.

Most implemented papers

Explicit Visual Prompting for Universal Foreground Segmentations

Chi-Man Pun, Weihuang Liu, Xiaodong Cun, Xi Shen•Sun May 28 2023

This paper takes inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and proposes a new visual prompting model, named Explicit Visual Prompting (EVP), which freezes a pre-trained model and then learns task-specific knowledge using a few extra parameters.

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Defocus Blur Detection via Depth Distillation

Chi-Man Pun, Xiaodong Cun•Wed Jul 15 2020

This work considers the depth information as the approximate soft label of DBD and proposes a joint learning framework inspired by knowledge distillation that learns the defocus blur from ground truth and the depth distilled from a well-trained depth estimation network at the same time.

30 0

Paper Graph

Self-generated Defocus Blur Detection via Dual Adversarial Discriminators

Huchuan Lu, Wenda Zhao, Cai Shang•Mon May 31 2021

Although existing fully-supervised defocus blur detection (DBD) models significantly improve performance, training such deep models requires abundant pixel-level manual annotation, which is highly time-consuming and error-prone. Addressing this issue, this paper makes an effort to train a deep DBD model without using any pixel-level annotation. The core insight is that a defocus blur region/focused clear area can be arbitrarily pasted to a given realistic full blurred image/full clear image without affecting the judgment of the full blurred image/full clear image. Specifically, we train a generator G in an adversarial manner against dual discriminators Dc and Db. G learns to produce a DBD mask that generates a composite clear image and a composite blurred image through copying the focused area and unfocused region from corresponding source image to another full clear image and full blurred image. Then, Dc and Db can not distinguish them from realistic full clear image and full blurred image simultaneously, achieving a self-generated DBD by an implicit manner to define what a defocus blur area is. Besides, we propose a bilateral triplet-excavating constraint to avoid the degenerate problem caused by the case one discriminator defeats the other one. Comprehensive experiments on two widely-used DBD datasets demonstrate the superiority of the proposed approach. Source codes are available at: https://github.com/shangcai1/SG.

28 0

Paper Graph

Explicit Visual Prompting for Low-Level Structure Segmentations

Chi-Man Pun, Weihuang Liu, Xiaodong Cun, Xi Shen•Sun Mar 19 2023

This work takes inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and proposes a new visual prompting model, named Explicit Visual Prompting (EVP), which significantly outperforms other parameter-efficient tuning protocols under the same amount of tunable parameters.

200 0

Paper Graph

Depth and DOF Cues Make A Better Defocus Blur Detector

Guisong Xia, Nan Xue, Yuxin Jin, Ming Qian, Jincheng Xiong•Mon Jun 19 2023

Inspired by the law of depth, depth of field (DOF), and defocus, an approach called D-DFFNet is proposed, which incorporates depth and DOF cues in an implicit manner, which allows the model to understand the defocus phenomenon in a more natural way.

6 0

Paper Graph

Equipping computational pathology systems with artifact processing pipelines: a showcase for computation and performance trade-offs

Neel Kanwal, Farbod Khoraminia, Umay Kiraz, Andrés Mosquera-Zamudio, Carlos Monteagudo, Emiel A. M. Janssen, T. Zuiverloon, Chunming Rong, K. Engan•Mon Mar 11 2024

A mixture of experts (MoE) scheme for detecting five notable artifacts, including damaged tissue, blur, folded tissue, air bubbles, and histologically irrelevant blood from WSIs, and the best-performing pipeline for artifact detection is MoE with DCNNs.

14 0

Paper Graph

Adding a benchmark result helps the community track progress.

Defocus Blur Detection | State-of-the-Art