Ha-Eun Ahn
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ha-Eun Ahn has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Je Woo Kim
Korea Electronics Technology Institute
2 shared publications - Jinwoo Jeong
Intelligent Semiconductor Device Research Center, Korea Electronics Technology Institute, Seongnam-si, Republic of Korea
2 shared publications - Jisang Yoo
Affiliation Department of Electronic Engineering, Kwangwoon University, Seoul, Republic of Korea
1 shared publication - Soonchul Kwon
Graduate School of Smart Convergence, Kwangwoon University, Seoul, Republic of Korea
1 shared publication
Latest Publications
- Open Access
A Fast 4K Video Frame Interpolation Using a Multi-Scale Optical Flow Reconstruction Network
Recently, video frame interpolation research developed with a convolutional neural network has shown remarkable results. However, these methods demand huge amounts of memory and run time for high-resolution videos, and are unable to process a 4K frame in a single pass. In this paper, we propose a fast 4K video frame interpolation method, based upon a multi-scale optical flow reconstruction scheme. The proposed method predicts low resolution bi-directional optical flow, and reconstructs it into high resolution. We also proposed consistency and multi-scale smoothness loss to enhance the quality of the predicted optical flow. Furthermore, we use adversarial loss to make the interpolated frame more seamless and natural. We demonstrated that the proposed method outperforms the existing state-of-the-art methods in quantitative evaluation, while it runs up to 4.39× faster than those methods for 4K videos.
Open AccessA Fast 4K Video Frame Interpolation Using a Multi-Scale Optical Flow Reconstruction Network
Recently, video frame interpolation research developed with a convolutional neural network has shown remarkable results. However, these methods demand huge amounts of memory and run time for high-resolution videos, and are unable to process a 4K frame in a single pass. In this paper, we propose a fast 4K video frame interpolation method, based upon a multi-scale optical flow reconstruction scheme. The proposed method predicts low resolution bi-directional optical flow, and reconstructs it into high resolution. We also proposed consistency and multi-scale smoothness loss to enhance the quality of the predicted optical flow. Furthermore, we use adversarial loss to make the interpolated frame more seamless and natural. We demonstrated that the proposed method outperforms the existing state-of-the-art methods in quantitative evaluation, while it runs up to 4.39× faster than those methods for 4K videos.
- Open Access
A Fast 4K Video Frame Interpolation Using a Hybrid Task-Based Convolutional Neural Network
Visual quality and algorithm efficiency are two main interests in video frame interpolation. We propose a hybrid task-based convolutional neural network for fast and accurate frame interpolation of 4K videos. The proposed method synthesizes low-resolution frames, then reconstructs high-resolution frames in a coarse-to-fine fashion. We also propose edge loss, to preserve high-frequency information and make the synthesized frames look sharper. Experimental results show that the proposed method achieves state-of-the-art performance and performs 2.69x faster than the existing methods that are operable for 4K videos, while maintaining comparable visual and quantitative quality.
Open AccessA Fast 4K Video Frame Interpolation Using a Hybrid Task-Based Convolutional Neural Network
Visual quality and algorithm efficiency are two main interests in video frame interpolation. We propose a hybrid task-based convolutional neural network for fast and accurate frame interpolation of 4K videos. The proposed method synthesizes low-resolution frames, then reconstructs high-resolution frames in a coarse-to-fine fashion. We also propose edge loss, to preserve high-frequency information and make the synthesized frames look sharper. Experimental results show that the proposed method achieves state-of-the-art performance and performs 2.69x faster than the existing methods that are operable for 4K videos, while maintaining comparable visual and quantitative quality.