Satoshi Kosugi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Satoshi Kosugi has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Toshihiko Yamasaki
The University of Tokyo
2 shared publications - Dongyuan Li
Center for Spatial Information Science, The University of Tokyo, Tokyo, Japan
1 shared publication - Feng Xia
School of Computing Technologies, RMIT University
1 shared publication - Manabu Okumura
Institute of Science Tokyo, Tokyo, Japan
1 shared publication - Renhe Jiang
The University of Tokyo, Tokyo, Japan
1 shared publication - Ying Zhang
RIKEN, Sendai, Japan
1 shared publication
Latest Publications
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 174557-174568
SSVG-Bench: Benchmarking Large Language Models on the Generation of Structured Scientific Vector Graphics
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 174557-174568
Open AccessSSVG-Bench: Benchmarking Large Language Models on the Generation of Structured Scientific Vector Graphics
- 26 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (10) , 10059-10069
Leveraging the Powerful Attention of a Pre-Trained Diffusion Model for Exemplar-Based Image Colorization
Exemplar-based image colorization aims to colorize a grayscale image using a reference color image, ensuring that reference colors are applied to corresponding input regions based on their semantic similarity. To achieve accurate semantic matching between regions, we leverage the self-attention module of a pre-trained diffusion model, which is trained on a large dataset and exhibits powerful attention capabilities. To harness this power, we propose a novel, fine-tuning-free approach based on a pre-trained diffusion model, making two key contributions. First, we introduce dual attention-guided color transfer. We utilize the self-attention module to compute an attention map between the input and reference images, effectively capturing semantic correspondences. The color features from the reference image is then transferred to the semantically matching regions of the input image, guided by this attention map, and finally, the grayscale features are replaced with the corresponding color features. Notably, we utilize dual attention to calculate attention maps separately for the grayscale and color images, achieving more precise semantic alignment. Second, we propose classifier-free colorization guidance, which enhances the transferred colors by combining color-transferred and non-color-transferred outputs. This process improves the quality of colorization. Our experimental results demonstrate that our method outperforms existing techniques in terms of image quality and fidelity to the reference. Specifically, we use 335 input-reference pairs from previous research, achieving an FID of 95.27 (image quality) and an SI-FID of 5.51 (fidelity to the reference). In addition, we evaluate on our novel dataset, which consists of 100 pairs of natural photos and historical paintings, achieving an FID of 219.05 and an SI-FID of 7.94. Our source code is available at https://github.com/satoshi-kosugi/powerful-attention.
- 26 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (10) , 10059-10069
Leveraging the Powerful Attention of a Pre-Trained Diffusion Model for Exemplar-Based Image Colorization
Exemplar-based image colorization aims to colorize a grayscale image using a reference color image, ensuring that reference colors are applied to corresponding input regions based on their semantic similarity. To achieve accurate semantic matching between regions, we leverage the self-attention module of a pre-trained diffusion model, which is trained on a large dataset and exhibits powerful attention capabilities. To harness this power, we propose a novel, fine-tuning-free approach based on a pre-trained diffusion model, making two key contributions. First, we introduce dual attention-guided color transfer. We utilize the self-attention module to compute an attention map between the input and reference images, effectively capturing semantic correspondences. The color features from the reference image is then transferred to the semantically matching regions of the input image, guided by this attention map, and finally, the grayscale features are replaced with the corresponding color features. Notably, we utilize dual attention to calculate attention maps separately for the grayscale and color images, achieving more precise semantic alignment. Second, we propose classifier-free colorization guidance, which enhances the transferred colors by combining color-transferred and non-color-transferred outputs. This process improves the quality of colorization. Our experimental results demonstrate that our method outperforms existing techniques in terms of image quality and fidelity to the reference. Specifically, we use 335 input-reference pairs from previous research, achieving an FID of 95.27 (image quality) and an SI-FID of 5.51 (fidelity to the reference). In addition, we evaluate on our novel dataset, which consists of 100 pairs of natural photos and historical paintings, achieving an FID of 219.05 and an SI-FID of 7.94. Our source code is available at https://github.com/satoshi-kosugi/powerful-attention.
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1342-1352
Revisiting Dynamic Graph Clustering via Matrix Factorization
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1342-1352
Open AccessRevisiting Dynamic Graph Clustering via Matrix Factorization
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 6463-6471
Prompt-Guided Image-Adaptive Neural Implicit Lookup Tables for Interpretable Image Enhancement
In this paper, we delve into the concept of interpretable image enhancement, a technique that enhances image quality by adjusting filter parameters with easily understandable names such as "Exposure'' and "Contrast''. Unlike using predefined image editing filters, our framework utilizes learnable filters that acquire interpretable names through training. Our contribution is two-fold. Firstly, we introduce a novel filter architecture called an image-adaptive neural implicit lookup table, which uses a multilayer perceptron to implicitly define the transformation from input feature space to output color space. By incorporating image-adaptive parameters directly into the input features, we achieve highly expressive filters. Secondly, we introduce a prompt guidance loss to assign interpretable names to each filter. We evaluate visual impressions of enhancement results, such as exposure and contrast, using a vision and language model along with guiding prompts. We define a constraint to ensure that each filter affects only the targeted visual impression without influencing other attributes, which allows us to obtain the desired filter effects. Experimental results show that our method outperforms existing predefined filter-based methods, thanks to the filters optimized to predict target results. Our source code is available at https://github.com/satoshi-kosugi/PG-IA-NILUT.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 6463-6471
Open AccessPrompt-Guided Image-Adaptive Neural Implicit Lookup Tables for Interpretable Image Enhancement
In this paper, we delve into the concept of interpretable image enhancement, a technique that enhances image quality by adjusting filter parameters with easily understandable names such as "Exposure'' and "Contrast''. Unlike using predefined image editing filters, our framework utilizes learnable filters that acquire interpretable names through training. Our contribution is two-fold. Firstly, we introduce a novel filter architecture called an image-adaptive neural implicit lookup table, which uses a multilayer perceptron to implicitly define the transformation from input feature space to output color space. By incorporating image-adaptive parameters directly into the input features, we achieve highly expressive filters. Secondly, we introduce a prompt guidance loss to assign interpretable names to each filter. We evaluate visual impressions of enhancement results, such as exposure and contrast, using a vision and language model along with guiding prompts. We define a constraint to ensure that each filter affects only the targeted visual impression without influencing other attributes, which allows us to obtain the desired filter effects. Experimental results show that our method outperforms existing predefined filter-based methods, thanks to the filters optimized to predict target results. Our source code is available at https://github.com/satoshi-kosugi/PG-IA-NILUT.
- 13 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (1) , 140-152
Personalized Image Enhancement Featuring Masked Style Modeling
We address personalized image enhancement in this study, where we enhance input images for each user based on the user’s preferred images. Previous methods apply the same preferred style to all input images ( i.e ., only one style for each user); in contrast to these methods, we aim to achieve content-aware personalization by applying different styles to each image considering the contents. For content-aware personalization, we make two contributions. First, we propose a method named masked style modeling, which can predict a style for an input image considering the contents by using the framework of masked language modeling. Second, to allow this model to consider the contents of images, we propose a novel training scheme where we download images from Flickr and create pseudo input and retouched image pairs using a degrading model. We conduct quantitative evaluations and a user study, and our method trained using our training scheme successfully achieves content-aware personalization; moreover, our method outperforms other previous methods in this field. Our source code is available at https://github.com/satoshi-kosugi/masked-style-modeling.
- 13 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (1) , 140-152
Personalized Image Enhancement Featuring Masked Style Modeling
We address personalized image enhancement in this study, where we enhance input images for each user based on the user’s preferred images. Previous methods apply the same preferred style to all input images ( i.e ., only one style for each user); in contrast to these methods, we aim to achieve content-aware personalization by applying different styles to each image considering the contents. For content-aware personalization, we make two contributions. First, we propose a method named masked style modeling, which can predict a style for an input image considering the contents by using the framework of masked language modeling. Second, to allow this model to consider the contents of images, we propose a novel training scheme where we download images from Flickr and create pseudo input and retouched image pairs using a degrading model. We conduct quantitative evaluations and a user study, and our method trained using our training scheme successfully achieves content-aware personalization; moreover, our method outperforms other previous methods in this field. Our source code is available at https://github.com/satoshi-kosugi/masked-style-modeling.
- 3 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 33 (7) , 3145-3158
Crowd-Powered Photo Enhancement Featuring an Active Learning Based Local Filter
In this study, we address local photo enhancement to improve the aesthetic quality of an input image by applying different effects to different regions. Existing photo enhancement methods are either not content-aware or not local; therefore, we propose a crowd-powered local enhancement method for content-aware local enhancement, which is achieved by asking crowd workers to locally optimize parameters for image editing functions. To make it easier to locally optimize the parameters, we propose an active learning based local filter. The parameters need to be determined at only a few key pixels selected by an active learning method, and the parameters at the other pixels are automatically predicted using a regression model. The parameters at the selected key pixels are independently optimized, breaking down the optimization problem into a sequence of single-slider adjustments. Our experiments show that the proposed filter outperforms existing filters, and our enhanced results are more visually pleasing than the results by the existing enhancement methods. Our source code and results are available at https://github.com/satoshi-kosugi/crowd-powered.
- 3 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 33 (7) , 3145-3158
Crowd-Powered Photo Enhancement Featuring an Active Learning Based Local Filter
In this study, we address local photo enhancement to improve the aesthetic quality of an input image by applying different effects to different regions. Existing photo enhancement methods are either not content-aware or not local; therefore, we propose a crowd-powered local enhancement method for content-aware local enhancement, which is achieved by asking crowd workers to locally optimize parameters for image editing functions. To make it easier to locally optimize the parameters, we propose an active learning based local filter. The parameters need to be determined at only a few key pixels selected by an active learning method, and the parameters at the other pixels are automatically predicted using a regression model. The parameters at the selected key pixels are independently optimized, breaking down the optimization problem into a sequence of single-slider adjustments. Our experiments show that the proposed filter outperforms existing filters, and our enhanced results are more visually pleasing than the results by the existing enhancement methods. Our source code and results are available at https://github.com/satoshi-kosugi/crowd-powered.