Search Results for author: Songchen Han

Found 5 papers, 5 papers with code

LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models

1 code implementation12 Jul 2024 Hai Jiang, Ao Luo, Xiaohong Liu, Songchen Han, Shuaicheng Liu

In this paper, we propose a diffusion-based unsupervised framework that incorporates physically explainable Retinex theory with diffusion models for low-light image enhancement, named LightenDiffusion.

Low-Light Image Enhancement

Supervised Homography Learning with Realistic Dataset Generation

1 code implementation ICCV 2023 Hai Jiang, Haipeng Li, Songchen Han, Haoqiang Fan, Bing Zeng, Shuaicheng Liu

In this paper, we propose an iterative framework, which consists of two phases: a generation phase and a training phase, to generate realistic training data and yield a supervised homography network.

Low-Light Image Enhancement with Wavelet-based Diffusion Models

1 code implementation1 Jun 2023 Hai Jiang, Ao Luo, Songchen Han, Haoqiang Fan, Shuaicheng Liu

Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration.

Denoising Face Detection +2

Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint

1 code implementation6 Dec 2022 Hai Jiang, Haipeng Li, Yuhang Lu, Songchen Han, Shuaicheng Liu

Homography estimation is erroneous in the case of large-baseline due to the low image overlay and limited receptive field.

Homography Estimation

R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network

1 code implementation28 Jun 2021 Jiang Hai, Zhu Xuan, Songchen Han, Ren Yang, Yutong Hao, Fengzhu Zou, Fang Lin

Solving a series of degradation of low-light images can effectively improve the visual quality of images and the performance of high-level visual tasks.

Denoising Face Detection +1

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