A novel approach to low-light image and video enhancement using adaptive dual super-resolution generative adversarial networks and top-hat filtering

Computers & Electrical Engineering, Год журнала: 2025, Номер 123, С. 110052 - 110052

Опубликована: Янв. 13, 2025

Язык: Английский

---

A Deformable Convolutional Neural Network for Video Super‐Resolution

Computational Intelligence, Год журнала: 2025, Номер 41(3)

Опубликована: Май 3, 2025

ABSTRACT Convolutional Neural Networks used deep architectures to achieve feature extraction in video super‐resolution. However, they suffered from challenges of rapid motion and complex scenes In this paper, we present a deformable convolutional neural network for super‐resolution (DVSRNet). DVSRNet mainly contains forward backward propagation blocks (FPBs), enhancement (FEBs), fusion block (FFB), reconstruction (RB). FPBs can leverage temporal sequence information capture rich dimensional To restore detailed information, an optical flow technique guided CNN align the obtained structural different frames reduce motion‐induced blur artifacts. address videos motioned objects, two FEBs utilized convolutions adaptively correct misaligned objects improve spatial continuity videos. reliability videos, FFB is integrate relations propagations. Finally, RB via upsampling operations residual learning construct high‐quality Experimental results demonstrate that our exhibits superior performance on multiple public datasets Its codes be available at https://github.com/leyoukai/DVSRNet .

Язык: Английский

---

Multiframe-to-multiframe network for underwater unpaired video enhancement

Displays, Год журнала: 2025, Номер unknown, С. 103063 - 103063

Опубликована: Май 1, 2025

---

LMAFormer: Local Motion Aware Transformer for Small Moving Infrared Target Detection

IEEE Transactions on Geoscience and Remote Sensing, Год журнала: 2024, Номер 62, С. 1 - 17

Опубликована: Янв. 1, 2024

Язык: Английский

---

Two-Stage Deep Image Restoration Network with Application to Single Image Shadow Removal

Applied Soft Computing, Год журнала: 2024, Номер unknown, С. 112315 - 112315

Опубликована: Окт. 1, 2024

Язык: Английский

---

Aggregating multi-scale flow-enhanced information in transformer for video inpainting

Multimedia Systems, Год журнала: 2024, Номер 31(1)

Опубликована: Дек. 29, 2024

Язык: Английский

---