publications | IIDA Lab

2025

CVPR

Channel-wise Noise Scheduled Diffusion for Inverse Rendering in Indoor Scenes

JunYong Choi, Min-Cheol Sagong, SeokYeong Lee, and 3 more authors

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

DOI Bib HTML PDF

@inproceedings{choi2025channelwise,
  title = {Channel-wise Noise Scheduled Diffusion for Inverse Rendering in Indoor Scenes},
  author = {Choi, JunYong and Sagong, Min-Cheol and Lee, SeokYeong and Jung, Seung-Won and Kim, Ig-Jae and Cho, Junghyun},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {5773--5782},
  doi = {10.1109/CVPR52734.2025.00542},
  year = {2025}
}

ICCV

VIGFace: Virtual Identity Generation for Privacy-Free Face Recognition Dataset

Minsoo Kim^*, Min-Cheol Sagong^*, Gi Pyo Nam, and 2 more authors

In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

@inproceedings{kim2025vigface,
  title = {{VIGFace}: Virtual Identity Generation for Privacy-Free Face Recognition Dataset},
  author = {Kim, Minsoo and Sagong, Min-Cheol and Nam, Gi Pyo and Cho, Junghyun and Kim, Ig-Jae},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages = {10043--10053},
  year = {2025}
}

AAAI

Multi-view pedestrian occupancy prediction with a novel synthetic dataset

Sithu Aung, Min-Cheol Sagong, and Junghyun Cho

Proceedings of the AAAI Conference on Artificial Intelligence, 2025

DOI Bib HTML PDF

@article{aung2025multiview,
  title = {Multi-view pedestrian occupancy prediction with a novel synthetic dataset},
  author = {Aung, Sithu and Sagong, Min-Cheol and Cho, Junghyun},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume = {39},
  number = {2},
  pages = {1782--1790},
  doi = {10.1609/AAAI.V39I2.32172},
  year = {2025}
}

2023

ICIP

Semantic and Instance-Aware Pixel-Adaptive Convolution for Panoptic Segmentation

Sumin Song, Min-Cheol Sagong, Seung-Won Jung, and 1 more author

In 2023 IEEE International Conference on Image Processing (ICIP), 2023

DOI Bib HTML PDF

@inproceedings{song2023semantic,
  title = {Semantic and Instance-Aware Pixel-Adaptive Convolution for Panoptic Segmentation},
  author = {Song, Sumin and Sagong, Min-Cheol and Jung, Seung-Won and Ko, Sung-Jea},
  booktitle = {2023 IEEE International Conference on Image Processing (ICIP)},
  pages = {16--20},
  publisher = {IEEE},
  doi = {10.1109/ICIP49359.2023.10222515},
  year = {2023}
}

Appl. Intell.

Image generation with self pixel-wise normalization

Yoon-Jae Yeo, Min-Cheol Sagong, Seung Park, and 2 more authors

Applied Intelligence, 2023

DOI Bib HTML PDF

@article{yeo2023image,
  title = {Image generation with self pixel-wise normalization},
  author = {Yeo, Yoon-Jae and Sagong, Min-Cheol and Park, Seung and Ko, Sung-Jea and Shin, Yong-Goo},
  journal = {Applied Intelligence},
  volume = {53},
  number = {8},
  pages = {9409--9423},
  publisher = {Springer US},
  doi = {10.1007/s10489-022-04007-z},
  year = {2023}
}

2022

TNNLS

Conditional convolution projecting latent vectors on condition-specific space

Min-Cheol Sagong, Yoon-Jae Yeo, Yong-Goo Shin, and 1 more author

IEEE Transactions on Neural Networks and Learning Systems, 2022

@article{sagong2022conditional,
  title = {Conditional convolution projecting latent vectors on condition-specific space},
  author = {Sagong, Min-Cheol and Yeo, Yoon-Jae and Shin, Yong-Goo and Ko, Sung-Jea},
  journal = {IEEE Transactions on Neural Networks and Learning Systems},
  volume = {35},
  number = {1},
  pages = {1386--1393},
  publisher = {IEEE},
  doi = {10.1109/TNNLS.2022.3172512},
  year = {2022}
}

BMVC

RORD: A Real-world Object Removal Dataset.

Min-Cheol Sagong^*, Yoon-Jae Yeo^*, Seung-Won Jung, and 1 more author

In BMVC, 2022

@inproceedings{sagong2022rord,
  title = {{RORD}: A Real-world Object Removal Dataset.},
  author = {Sagong, Min-Cheol and Yeo, Yoon-Jae and Jung, Seung-Won and Ko, Sung-Jea},
  booktitle = {BMVC},
  pages = {542},
  year = {2022}
}

2021

arXiv

Content-aware directed propagation network with pixel adaptive kernel attention

Min-Cheol Sagong, Yoon-Jae Yeo, Seung-Won Jung, and 1 more author

arXiv preprint arXiv:2107.13144, 2021

arXiv Bib HTML PDF

@article{sagong2021contentaware,
  title = {Content-aware directed propagation network with pixel adaptive kernel attention},
  author = {Sagong, Min-Cheol and Yeo, Yoon-Jae and Jung, Seung-Won and Ko, Sung-Jea},
  journal = {arXiv preprint arXiv:2107.13144},
  year = {2021}
}

GCCE

Efficient Pyramid-Structured Networks Using Channel Separating Gate

Yoon-Jae Yeo, Min-Cheol Sagong, Sung-Jea Ko, and 1 more author

In 2021 IEEE 10th Global Conference on Consumer Electronics (GCCE), 2021

DOI Bib HTML PDF

@inproceedings{yeo2021efficient,
  title = {Efficient Pyramid-Structured Networks Using Channel Separating Gate},
  author = {Yeo, Yoon-Jae and Sagong, Min-Cheol and Ko, Sung-Jea and Lim, Dong-Pan},
  booktitle = {2021 IEEE 10th Global Conference on Consumer Electronics (GCCE)},
  pages = {986--987},
  publisher = {IEEE},
  doi = {10.1109/GCCE53005.2021.9621933},
  year = {2021}
}

2020

TNNLS

PEPSI++: Fast and lightweight network for image inpainting

Yong-Goo Shin, Min-Cheol Sagong, Yoon-Jae Yeo, and 2 more authors

IEEE Transactions on Neural Networks and Learning Systems, 2020

DOI Bib HTML PDF

@article{shin2020pepsipp,
  title = {{PEPSI}++: Fast and lightweight network for image inpainting},
  author = {Shin, Yong-Goo and Sagong, Min-Cheol and Yeo, Yoon-Jae and Kim, Seung-Wook and Ko, Sung-Jea},
  journal = {IEEE Transactions on Neural Networks and Learning Systems},
  volume = {32},
  number = {1},
  pages = {252--265},
  publisher = {IEEE},
  doi = {10.1109/TNNLS.2020.2978501},
  year = {2020}
}

SPL

Simple yet effective way for improving the performance of depth map super-resolution

Yoon-Jae Yeo, Min-Cheol Sagong, Yong-Goo Shin, and 2 more authors

IEEE Signal Processing Letters, 2020

DOI Bib HTML PDF

@article{yeo2020depthmap,
  title = {Simple yet effective way for improving the performance of depth map super-resolution},
  author = {Yeo, Yoon-Jae and Sagong, Min-Cheol and Shin, Yong-Goo and Jung, Seung-Won and Ko, Sung-Jea},
  journal = {IEEE Signal Processing Letters},
  volume = {27},
  pages = {2099--2103},
  publisher = {IEEE},
  doi = {10.1109/LSP.2020.3039429},
  year = {2020}
}

SPL

Simple yet effective way for improving the performance of lossy image compression

Yoon-Jae Yeo, Yong-Goo Shin, Min-Cheol Sagong, and 2 more authors

IEEE Signal Processing Letters, 2020

DOI Bib HTML PDF

@article{yeo2020lossy,
  title = {Simple yet effective way for improving the performance of lossy image compression},
  author = {Yeo, Yoon-Jae and Shin, Yong-Goo and Sagong, Min-Cheol and Kim, Seung-Wook and Ko, Sung-Jea},
  journal = {IEEE Signal Processing Letters},
  volume = {27},
  pages = {530--534},
  publisher = {IEEE},
  doi = {10.1109/LSP.2020.2982561},
  year = {2020}
}

2019

CVPR

PEPSI: Fast image inpainting with parallel decoding network

Min-Cheol Sagong, Yong-Goo Shin, Seung-Wook Kim, and 2 more authors

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019

DOI Bib HTML PDF

@inproceedings{sagong2019pepsi,
  title = {{PEPSI}: Fast image inpainting with parallel decoding network},
  author = {Sagong, Min-Cheol and Shin, Yong-Goo and Kim, Seung-Wook and Park, Seung and Ko, Sung-Jea},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {11360--11368},
  doi = {10.1109/CVPR.2019.01162},
  year = {2019}
}

ICCE-Berlin

Deep fashion recommendation system with style feature decomposition

Yong-Goo Shin, Yoon-Jae Yeo, Min-Cheol Sagong, and 2 more authors

In 2019 IEEE 9th International Conference on Consumer Electronics (ICCE-Berlin), 2019

DOI Bib HTML PDF

@inproceedings{shin2019fashion,
  title = {Deep fashion recommendation system with style feature decomposition},
  author = {Shin, Yong-Goo and Yeo, Yoon-Jae and Sagong, Min-Cheol and Ji, Seo-Won and Ko, Sung-Jea},
  booktitle = {2019 IEEE 9th International Conference on Consumer Electronics (ICCE-Berlin)},
  pages = {301--305},
  publisher = {IEEE},
  doi = {10.1109/ICCE-Berlin47944.2019.8966228},
  year = {2019}
}

2018

DICTA

Adversarial context aggregation network for low-light image enhancement

Yong-Goo Shin, Min-Cheol Sagong, Yoon-Jae Yeo, and 1 more author

In 2018 Digital Image Computing: Techniques and Applications (DICTA), 2018

@inproceedings{shin2018lowlight,
  title = {Adversarial context aggregation network for low-light image enhancement},
  author = {Shin, Yong-Goo and Sagong, Min-Cheol and Yeo, Yoon-Jae and Ko, Sung-Jea},
  booktitle = {2018 Digital Image Computing: Techniques and Applications (DICTA)},
  pages = {1--5},
  publisher = {IEEE},
  doi = {10.1109/DICTA.2018.8615848},
  year = {2018}
}