Video Super-Resolution Network with Gated High-Low Resolution Frames

Article Computer Science, Artificial Intelligence

Multi-frame super-resolution of remote sensing images using attention-based GAN models

Peijuan Wang et al.

Summary: With the advancement of artificial intelligence techniques and the launch of new satellites with video capturing capability, multi-frame super-resolution of remote sensing images has become a critical research topic. In this study, an attention-based Generative Adversarial Network (GAN) algorithm is proposed for multi-frame remote sensing image super-resolution. Several experiments were conducted, comparing the results of different models and the proposed approach using SpaceNet7 and Jilin-1 datasets.

KNOWLEDGE-BASED SYSTEMS (2023)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

BasicVSR plus plus : Improving Video Super-Resolution with Enhanced Propagation and Alignment

Kelvin C. K. Chan et al.

Summary: This study proposes second-order grid propagation and flow-guided deformable alignment to enhance the recurrent framework of video super-resolution method BasicVSR. The new components improve the performance and achieve good results in the NTIRE 2021 video restoration challenge.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Stable Long-Term Recurrent Video Super-Resolution

Benjamin Naoto Chiche et al.

Summary: In this paper, the instability of existing recurrent VSR networks on long sequences with low motion is investigated, and a stable and competitive solution is proposed based on a new framework of recurrent VSR networks.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Omniscient Video Super-Resolution

Peng Yi et al.

Summary: This study introduces an omniscient framework that utilizes previous, current, and future SR outputs, allowing the generator to perform better across various frameworks. Abundant experiments demonstrate that the proposed method outperforms existing methods in objective metrics, subjective visual effects, and complexity.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Optical Flow Enhancement and Effect Research in Action Recognition

Hai Li et al.

Summary: This article discusses the impact of optical flow on the accuracy of action recognition and proposes optical flow enhancement algorithms to improve accuracy. Through a series of experiments, the effectiveness of the enhancement algorithms and the importance of invariance to appearance in optical flow are validated.

2021 IEEE 13TH INTERNATIONAL CONFERENCE ON COMPUTER RESEARCH AND DEVELOPMENT (ICCRD 2021) (2021)

Add to Collection

Article Computer Science, Artificial Intelligence