Publications

2026

1. 

   

   Splat-Based Metal Artifact Reduction in Cone-Beam CT via Compact Attenuation Modeling

   Kiseok Choi, Jaemin Cho, Inchul Kim, and Min H. Kim

   In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026

   summary Bib

   We propose our compact attenuation model, enabling effective CBCT reconstruction with reduced metal-induced artifacts without a metal mask.

   @inproceedings{cbct_mar:cvpr:2026,
     author = {Choi, Kiseok and Cho, Jaemin and Kim, Inchul and Kim, Min H.},
     title = {Splat-Based Metal Artifact Reduction in Cone-Beam CT via Compact Attenuation Modeling},
     booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2026},
   }

2. Revisiting Pose Sensitivity in Splat-based Computed Tomography under Sparse-view Reconstruction

   Kiseok Choi, Hyeongjun Cho, Inchul Kim, and Min H. Kim

   In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026

   summary Bib

   Our CBCT reconstructs a volume under sparse number of projections with severe pose perturbations.

   @inproceedings{cbct_pose:cvpr:2026,
     author = {Choi, Kiseok and Cho, Hyeongjun and Kim, Inchul and Kim, Min H.},
     title = {Revisiting Pose Sensitivity in Splat-based Computed Tomography under Sparse-view Reconstruction},
     booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2026},
   }

3. 

   

   Splat-based Metal Artifact Reduction in Cone-Beam CT via Polychromatic Modeling

   Kiseok Choi, Inchul Kim, Jaemin Cho, Hyeongjun Cho, and Min H. Kim

   Computer Graphics Forum (Proc. Eurographics), 2026

   summary Project PDF Supp DOI Bib

   A physics-inspired, CBCT method that reduces metal-induced beam hardening artifacts with polychromatic modeling and Gaussian Splatting.

   @article{cbctmar:cgf:2026,
     author = {Choi, Kiseok and Kim, Inchul and Cho, Jaemin and Cho, Hyeongjun and Kim, Min H.},
     title = {Splat-based Metal Artifact Reduction in Cone-Beam CT via Polychromatic Modeling},
     journal = {Computer Graphics Forum (Proc. Eurographics)},
     year = {2026},
     doi = {10.1111/cgf.70339},
   }

2023

1. Self-Calibrating, Fully Differentiable NLOS Inverse Rendering

   Kiseok Choi, Inchul Kim, Dongyoung Choi, Julio Marco, Diego Gutierrez, and Min H. Kim

   In Proceedings of ACM SIGGRAPH Asia, 2023

   summary Project PDF Supp Code DOI Bib

   We present a flexible, differentiable non-line-of-sight (NLOS) imaging and rendering pipeline that automatically estimates system parameters and the geometry of hidden objects.

   @inproceedings{nlos:siga:2023,
     author = {Choi, Kiseok and Kim, Inchul and Choi, Dongyoung and Marco, Julio and Gutierrez, Diego and Kim, Min H.},
     title = {Self-Calibrating, Fully Differentiable NLOS Inverse Rendering},
     booktitle = {Proceedings of ACM SIGGRAPH Asia},
     year = {2023},
     doi = {10.1145/3610548.3618140},
   }

2. 

   

   

   Spatio-Focal Bidirectional Disparity Estimation from a Dual-Pixel Image

   Donggun Kim, Hyeonjoong Jang, Inchul Kim, and Min H. Kim

   In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023

   summary Project PDF Supp Code DOI Bib

   We estimate bidirectional disparities from a dual-pixel image by a network using self-supervised learning. Our method based on the dual-pixel optics produces more physically correct results.

   @inproceedings{dp:cvpr:2023,
     author = {Kim, Donggun and Jang, Hyeonjoong and Kim, Inchul and Kim, Min H.},
     title = {Spatio-Focal Bidirectional Disparity Estimation from a Dual-Pixel Image},
     booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2023},
     doi = {10.1109/CVPR52729.2023.00486},
   }

2019

1. 

   Motion Parallax for 360° RGBD Video

   Ana Serrano, Incheol Kim, Zhili Chen, Stephen DiVerdi, Diego Gutierrez, Aaron Hertzmann, and Belén Masiá

   IEEE Transactions on Visualization and Computer Graphics (TVCG), 2019

   Best journal paper nominee (click)

   summary Project PDF Supp Slides Code DOI Bib

   Our VR video viewer exploits motion parallax cues to reduce VR sickness without additional hardware requirements. Our system provides a compelling viewing experience with reduced discomfort.

   @article{vrmotion:tvcg:2019,
     title = {Motion Parallax for 360° RGBD Video},
     author = {Serrano, Ana and Kim, Incheol and Chen, Zhili and DiVerdi, Stephen and Gutierrez, Diego and Hertzmann, Aaron and Masi{\'{a}}, Bel{\'{e}}n},
     journal = {IEEE Transactions on Visualization and Computer Graphics (TVCG)},
     volume = {25},
     number = {5},
     pages = {1817--1827},
     year = {2019},
     publisher = {IEEE},
     doi = {10.1109/TVCG.2019.2898757},
   }

2. 

   Non-local Haze Propagation with an Iso-Depth Prior

   Incheol Kim and Min H. Kim

   In Computer Vision, Imaging and Computer Graphics – Theory and Applications, 2019

   summary Project PDF Supp Code DOI Bib

   More experiments and validations have been added on top of our non-local haze regularization paper in 2017.

   @inproceedings{dehazing:ccis:2019,
     author = {Kim, Incheol and Kim, Min H.},
     title = {Non-local Haze Propagation with an Iso-Depth Prior},
     booktitle = {Computer Vision, Imaging and Computer Graphics -- Theory and Applications},
     year = {2019},
     publisher = {Springer International Publishing},
     pages = {213--238},
     isbn = {978-3-030-12209-6},
     doi = {10.1007/978-3-030-12209-6\_11},
   }

2017

1. 

   Compact Single-Shot Hyperspectral Imaging Using a Prism

   Seung-Hwan Baek, Incheol Kim, Diego Gutierrez, and Min H. Kim

   ACM Transactions on Graphics (Proc. SIGGRAPH Asia), 2017

   Press release: EurekAlert! / Photonics / R&D Magazine

   summary Project PDF Supp1 Supp2 DOI Bib

   Our compact snapshot hyperspectral imaging (HSI) system enables hand-held imaging spectroscopy, and shows strong performance over large HSI systems.

   @article{prism:siga:2017,
     author = {Baek, Seung-Hwan and Kim, Incheol and Gutierrez, Diego and Kim, Min H.},
     title = {Compact Single-Shot Hyperspectral Imaging Using a Prism},
     journal = {ACM Transactions on Graphics (Proc. SIGGRAPH Asia)},
     year = {2017},
     volume = {36},
     number = {6},
     pages = {217:1-12},
     doi = {10.1145/3130800.3130896},
   }

2. 

   

   Dehazing using Non-local Regularization with Iso-depth Neighbor-Fields

   Incheol Kim and Min H. Kim

   In Proc. Int. Conf. Computer Vision, Theory and Applications (VISAPP), 2017

   Oral Presentation

   summary Project PDF Supp Code DOI Bib

   Our haze regularization exploits non-local information from nearest-neighbor fields and shows the state-of-the-art performance.

   @inproceedings{dehazing:visapp:2017,
     author = {Kim, Incheol and Kim, Min H.},
     title = {Dehazing using Non-local Regularization with Iso-depth Neighbor-Fields},
     booktitle = {Proc. Int. Conf. Computer Vision, Theory and Applications (VISAPP)},
     pages = {77--88},
     year = {2017},
     doi = {10.5220/0006132400770088},
   }