Min Yoon
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Min Yoon has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Byung Cheol Song
Department of Electrical and Computer Engineering, Inha University, Incheon 22212, Republic of Korea
2 shared publications - Seunghyun Lee
Department of Electrical and Computer Engineering, Inha University, Incheon, Republic of Korea
2 shared publications - Junmin Lee
Department of Electrical and Computer Engineering, Inha University, Incheon, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 23 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 29154-29165
Real-Time Monte Carlo Denoising With Adaptive Fusion Network
Real-time Monte Carlo denoising aims to denoise a 1spp-rendered image with a limited time budget. Many latest techniques for real-time Monte Carlo denoising utilize temporal accumulation (TA) as a pre-processing to improve the temporal stability of successive frames and increase the effective spp. However, existing techniques using TA used to suffer from significant performance degradation when TA does not work well. In addition, they have the disadvantage of deteriorating performance in dynamic scenes because pixel information of the current frame cannot be sufficiently utilized due to the pixel averaging effect between temporally adjacent frames. To solve this problem, this paper proposes a framework that utilizes both 1spp images and temporally accumulated 1spp (TA-1spp) images. First, the multi-scale kernel prediction module estimates kernel maps for filtering 1spp images and TA-1spp images, respectively. Then, the filtered images are properly fused so that the two advantages of 1spp and TA-1spp images can create synergy. Also, the remaining noise is removed through the refinement module and fine details are reconstructed to improve the model flexibility, beyond using only the kernel prediction module. As a result, we achieve better quantitative and qualitative performance at 39% faster than state-of-the-art (SOTA) real-time Monte Carlo denoisers.
- 23 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 29154-29165
Open AccessReal-Time Monte Carlo Denoising With Adaptive Fusion Network
Real-time Monte Carlo denoising aims to denoise a 1spp-rendered image with a limited time budget. Many latest techniques for real-time Monte Carlo denoising utilize temporal accumulation (TA) as a pre-processing to improve the temporal stability of successive frames and increase the effective spp. However, existing techniques using TA used to suffer from significant performance degradation when TA does not work well. In addition, they have the disadvantage of deteriorating performance in dynamic scenes because pixel information of the current frame cannot be sufficiently utilized due to the pixel averaging effect between temporally adjacent frames. To solve this problem, this paper proposes a framework that utilizes both 1spp images and temporally accumulated 1spp (TA-1spp) images. First, the multi-scale kernel prediction module estimates kernel maps for filtering 1spp images and TA-1spp images, respectively. Then, the filtered images are properly fused so that the two advantages of 1spp and TA-1spp images can create synergy. Also, the remaining noise is removed through the refinement module and fine details are reconstructed to improve the model flexibility, beyond using only the kernel prediction module. As a result, we achieve better quantitative and qualitative performance at 39% faster than state-of-the-art (SOTA) real-time Monte Carlo denoisers.
- Open Access
- 11 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 112015-112026
TAKDSR: Teacher Assistant Knowledge Distillation Framework for Graphics Image Super-Resolution
This paper presents a framework for effectively applying knowledge distillation (KD) to super-resolution (SR) tasks for computer graphics (CG) images. Specifically, we propose TAKDSR, a KD framework for SR using a teacher assistant (TA) network. Recently, the performance of SR models has improved dramatically thanks to the development of deep learning. SR models have evolved into a form that requires a considerable amount of computation and parameters while adopting a complex neural network structure to improve performance. However, it is difficult to utilize conventional high-performance SR models for real-time up-scaling in CG applications requiring high resolution and high frame rate. To solve this, we employ an approach that applies KD to a lightweight SR model. At this time, if the high-resolution (HR) image is used as input for the teacher to show superior performance to the student, a large performance difference occurs between the two due to the excessive performance of the teacher. As a result, the teacher’s knowledge has a significantly hard and complex nature, and when transferred to the student, the effect of KD can be rather weakened. Therefore, we adopt a TA network to facilitate the propagation of knowledge between teacher and student. At the same time, the distribution of compact features (CF), which are the decoder input of the teacher, is discretized so that it is compatible with the input distribution of the student, enabling effective KD. Experimental results demonstrate the proposed TAKDSR significantly improves the performance of a given SR model on CG image datasets.
- 11 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 112015-112026
Open AccessTAKDSR: Teacher Assistant Knowledge Distillation Framework for Graphics Image Super-Resolution
This paper presents a framework for effectively applying knowledge distillation (KD) to super-resolution (SR) tasks for computer graphics (CG) images. Specifically, we propose TAKDSR, a KD framework for SR using a teacher assistant (TA) network. Recently, the performance of SR models has improved dramatically thanks to the development of deep learning. SR models have evolved into a form that requires a considerable amount of computation and parameters while adopting a complex neural network structure to improve performance. However, it is difficult to utilize conventional high-performance SR models for real-time up-scaling in CG applications requiring high resolution and high frame rate. To solve this, we employ an approach that applies KD to a lightweight SR model. At this time, if the high-resolution (HR) image is used as input for the teacher to show superior performance to the student, a large performance difference occurs between the two due to the excessive performance of the teacher. As a result, the teacher’s knowledge has a significantly hard and complex nature, and when transferred to the student, the effect of KD can be rather weakened. Therefore, we adopt a TA network to facilitate the propagation of knowledge between teacher and student. At the same time, the distribution of compact features (CF), which are the decoder input of the teacher, is discretized so that it is compatible with the input distribution of the student, enabling effective KD. Experimental results demonstrate the proposed TAKDSR significantly improves the performance of a given SR model on CG image datasets.