Kai Katsumata

Kai Katsumata

Ph.D. student

The University of Tokyo

Biography

I’m a Ph.D. student at the University of Tokyo.

Interests
  • Computer Vision
  • Computer Graphics
  • Machine Learning
Education
  • Master of Information Science and Technology, 2022

    The University of Tokyo

  • Bachelor of Arts in Environment and Information Studies, 2020

    Keio University

News

2024

Our paper "A Compact Dynamic 3D Gaussian Representation for Real-Time Dynamic View Synthesis" have been accepted at ECCV 2024.
I will attend International Computer Vision Summer School 2024.

2023

3 papers have been accepeted at WACV 2024.

Recent Publications

Quickly discover relevant content by filtering publications.
(2024). Label Augmentation as Inter-class Data Augmentation for Conditional Image Synthesis with Imbalanced Data. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).

PDF Cite Code

(2024). Revisiting Latent Space of GAN Inversion for Real Image Editing. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).

PDF Cite Code

(2024). Soft Curriculum for Learning Conditional GANs with Noisy-Labeled and Uncurated Unlabeled Data. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).

PDF Cite Code

(2023). An Efficient 3D Gaussian Representation for Monocular/Multi-view Dynamic Scenes. arXiv preprint arXiv:2311.12897.

Cite Code URL

(2023). Balancing Reconstruction and Editing Quality of GAN Inversion for Real Image Editing with StyleGAN Prior Latent Space. arXiv preprint arXiv:2306.00241.

Cite URL

(2022). OSSGAN: Open-Set Semi-Supervised Image Generation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

PDF Cite Code

(2021). Open-set domain generalization via metric learning. IEEE International Conference on Image Processing (ICIP).

Cite URL

(2021). Semantic Image Synthesis from Inaccurate and Coarse Masks. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Cite URL

(2020). Uncertainty Estimates in Deep Generative Models Using Gaussian Processes. International Symposium on Visual Computing.

Cite URL

Experience

Preferred Networks - Research Intern Aug 2022 – Sep 2022 Tokyo
Research in human image generation and visual artifact removal.
Idein - Part-time Software Engineer Apr 2017 – Apr 2021 Tokyo
Developed face landmark detection algorithm
SenseTime - Research Intern Feb 2018 – Jun 2018 Beijing and Tokyo
Research in unsupervised image-to-image translation for data augmentation
DeNA - AI Research and Development Intern Aug 2017 – Sep 2017 Tokyo
Research in realtime superresolution