目录
代码-调色
- (CVPR2022) AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement-code
在3D LUT基础上,考虑自适应采样间隔,根据颜色分布密集程度来采样;
具体地:使用低分辨率输入和网络,预测LUT参数和采样坐标(分别预测三个颜色采样坐标并笛卡尔积得到三维坐标);
增加少量参数,训练得到结果提升;25.29--25.49
- (ECCV2022) Neural Color Operators for Sequential Image Retouching code
- (ICCV2021) Deep Symmetric Network for Underexposed Image Enhancement with Recurrent Attentional Learning- code
- (ICCV2021) Seeing Dynamic Scene in the Dark: A High-Quality Video Dataset with Mechatronic Alignment- code
- (CVPR 2021) Learning Multi-Scale Photo Exposure Correction" code
- (TPAMI2020) *Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time code
3个3D LUT basic block;
3个loss;平滑项+正则化+total variable loss
低分辨率分支学习三个block参数;
- (ECCV 2020) PieNet: Personalized Image Enhancement Network code
- (ECCV 2020) Global and Local Enhancement Networks for Paired and Unpaired Image Enhancement code
- (ECCV 2020) Conditional Sequential Modulation for Efficient Global Image Retouching code
- (CVPR 2020) *Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement code
Zero-DCE,使用卷积学习输入图片特征,分解为8个RGB三通道控制参数;
分别迭代调整8次图片曲线,得到最终增强图片;
利用空间差异性loss,颜色一致性loss和曝光经验参数控制loss优化训练过程;
- (CVPR 2019) *Underexposed Photo Enhancement using Deep Illumination Estimation code pytorch_code
- (NeurIPS 2019) Overparametrization of HyperNetworks at Fixed FLOP-Count Enables Fast Neural Image Enhancement code
代码-低光照
- Xu_SNR-Aware_Low-Light_Image_Enhancement_CVPR_2022_paper code
- CVPR2022-URetinex-Net: Retinex-based Deep Unfolding Network for Low-light Image Enhancement code
- Toward Fast, Flexible, and Robust Low-Light Image Enhancement, CVPR 2022 (Oral) code
- [TPAMI 2022] Learning Enriched Features for Fast Image Restoration and Enhancement. Results on Defocus Deblurring, Denoising, Super-resolution, and image enhancement code
- [ICCV 2021 Oral] StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement code
- Deep Symmetric Network for Underexposed Image Enhancement with Recurrent Attentional Learning (ICCV 2021) code
- [TNNLS 2021] The official code for the paper "Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement" code
- (ACMMM2021) ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement code paper 链接
- [IEEE TIP'2021] "EnlightenGAN: Deep Light Enhancement without Paired Supervision code
- [TIP2020] Pytorch implementation of "Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network" code
- Code for CVPR 2020 paper "Deep Local Parametric Filters for Image Enhancement"
- TMM2020 Deep Stacked Laplacian Restorer for Low-light Image Enhancement code
- ECCV2018 Champion solution of the PIRM2018 Challenge on Perceptual Image Enhancement on Smartphones code
- 低光照代码合集 code
数据集
*PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency", CVPR 2021 code