Search Results for author: Zhe-Ming Lu

Found 4 papers, 2 papers with code

Prompt-based test-time real image dehazing: a novel pipeline

1 code implementation29 Sep 2023 Zixuan Chen, Zewei He, Ziqian Lu, Xuecheng Sun, Zhe-Ming Lu

We experimentally find that given a dehazing model trained on synthetic data, by fine-tuning the statistics (i. e., mean and standard deviation) of encoding features, PTTD is able to narrow the domain gap, boosting the performance of real image dehazing.

Image Dehazing

Accurate and lightweight dehazing via multi-receptive-field non-local network and novel contrastive regularization

no code implementations28 Sep 2023 Zewei He, Zixuan Chen, Ziqian Lu, Xuecheng Sun, Zhe-Ming Lu

Thus, a multi-receptive-field non-local network (MRFNLN) consisting of the multi-stream feature attention block (MSFAB) and cross non-local block (CNLB) is presented in this paper.

Image Dehazing

A Monkey Swing Counting Algorithm Based on Object Detection

no code implementations12 Mar 2023 Hao Chen, Zhe-Ming Lu, Jie Liu

This paper focuses on proposing a deep learning-based monkey swing counting algorithm.

object-detection Object Detection

DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention

1 code implementation12 Jan 2023 Zixuan Chen, Zewei He, Zhe-Ming Lu

In this paper, a detail-enhanced attention block (DEAB) consisting of the detail-enhanced convolution (DEConv) and the content-guided attention (CGA) is proposed to boost the feature learning for improving the dehazing performance.

Image Dehazing

Cannot find the paper you are looking for? You can Submit a new open access paper.