Daichi Horita

I am a final-year Ph.D. candidate in the University of Tokyo at Aizawa Lab.
My research areas are computer vision and graphics. I am working on content creation using diffusion models and GANs.

CV  /  Email  /  Google Scholar  /  Twitter  /  Github

profile photo
Announcement

I'm looking for a research internship. I enthusiastically want to conduct a novel research. My current theme is on diffusion models. If you are interested in my research, please contact me via email or twitter.

Education

The University of Tokyo
Ph.D. in Graduate School of Information Science and Technology
Supervisor: Prof. Kiyoharu Aizawa
2022.4 - 2025.3 (Expected)

The University of Tokyo
M.S. in Graduate School of Interdisciplinary Information Studies
Supervisor: Prof. Kiyoharu Aizawa
2020.4 - 2022.3

The University of Electro-Communications
B.S. in Mechano Engineering
Supervisor: Prof. Keiji Yanai and Prof. Toma Sogabe
2016.4 - 2020.3

Work Experience

CyberAgent AI Lab
Research internship on creative research with Dr. Naoto Inoue, Dr. Kota Yamaguchi, Dr. Kotaro Kikuchi, and wonderful members!
August 2023 - November 2023
[Webpage]

University of Trento
Study abroad. I conducted a research under Prof. Nicu Sebe at an MHUG group. The visiting was fully funded by Erasmus+ ICM. Thanks, Nicu and MHUG cool guys!
Jan 2023 - July 2023
[MHUG Webpage]

Preferred Networks.
Project Engineer
April 2021 - Jun 2022
[Webpage]

Recruit Holdings Co., Ltd..
R&D Internship
Oct 2020 - Dec 2020
[Webpage]

Preferred Networks.
Research Internship
Aug 2020 - Oct 2020
[Webpage]

ZOZO Technologies, Inc.
Research Internship
with Hayato Maki, Ph.D.
April 2018 - Jun 2019
[Webpage]

Retty Inc.
Software Engineer Internship
Sep 2018 - Mar 2019
[Webpage]

Clue Inc.
Drone Software Engineer Internship
Mar 2017 - Nov 2017
[Webpage]

Publication

[18] Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation
Daichi Horita, Naoto Inoue, Kotaro Kikuchi, Kota Yamaguchi, and Kiyoharu Aizawa
In CVPR, Oral, 2024.
[Paper] [Project] [Code]
Out of 11,532 submissions, it's in the top 90 (top 0.78%) and among the 2,719 accepted papers (top 3.3%)!
We provide an all-in-one package for content-aware layout generation!

[17] A Structure-Guided Diffusion Model for Large-Hole Image Completion
Daichi Horita, Jiaolong Yang, Dong Chen, Yuki Koyama, Kiyoharu Aizawa, and Nicu Sebe
In BMVC, 2023.
[Paper] [Project]

[16] Restorable Visible and Infrared Image Fusion
Jihun Kang, Daichi Horita, Koki Tsubota, and Kiyoharu Aizawa
In ICIP, 2023.
[Paper]

[15] SLGAN: Style- and Latent-guided Generative Adversarial Network for Desirable Makeup Transfer and Removal
Daichi Horita, and Kiyoharu Aizawa
In ACM Multimedia Asia, 2022 (acceptance rate 30%).
[Paper]

[14] Translation of Illustration Artist Style Using Sailormoonredraw Data
Keita Awane, Daichi Horita, Hikaru Ikuta, Yusuke Matsui, Kiyoharu Aizawa, and Naohiro Yanase
In ICIP, 2022 (acceptance rate 48%).
[Paper]

[13] Ukemochi: A Video See-through Food Overlay System for Eating Experience in the Metaverse Kizashi Nakano, Daichi Horita, Naoya Isoyama, Hideki Uchiyama, and Kiyoshi Kiyokawa
In CHI Late Breaking Works, 2022 (acceptance rate 33%).
[Paper] [Video]

[12] Fast Nonlinear Image Unblending
Daichi Horita, Kiyoharu Aizawa, Ryohei Suzuki, Taizan Yonetsuji, and Huachun Zhu
In WACV, 2022 (acceptance rate 35%).
[Paper]

[11] Food Image Generation and Translation and Its Application to Augmented Reality
Keiji Yanai, Daichi Horita, and Jaehyeong Cho
In MIPR, 2020.
[Paper]

[10] SSA-GAN: End-to-End Time-Lapse Video Generation with Spatial Self-Attention
Daichi Horita, and Keiji Yanai
In ACPR, 2020 (acceptance rate 45%).
[Paper]

[9] DeepTaste: Augmented Reality Gustatory Manipulation with GAN-based Real-time Food-to-food Translation
Kizashi Nakano*, Daichi Horita*, Nobuchika Sakata, Kiyoshi Kiyokawa, Keiji Yanai, and Takuji Narumi (*) equally contributed
In ISMAR, oral, 2019 (acceptance rate 22%).
[Paper]

[8] Unseen Food Creation by Mixing Existing Food Images with Conditional StyleGAN
Daichi Horita, and Keiji Yanai
In ACM Multimedia Workshop, 2019.
[Paper]

[7] Large-scale Twitter Food Photo Mining and Its Applications
Keiji Yanai, Kaimu Okamoto, Tetsuya Nagano, and Daichi Horita
In BIGMM, 2019.
[Paper]

[6] Enchanting Your Noodles: GAN-based Real-time Food-to-Food Translation and Its Impact on Vision-induced Gustatory Manipulation
Kizashi Nakano*, Daichi Horita*, Nobuchika Sakata, Kiyoshi Kiyokawa, Keiji Yanai, and Takuji Narumi (*) equally contributed
In IEEE VR, demo, 2019.
[Paper]

[5] Enchanting Your Noodles: A Gustatory Manipulation Interface by Using GAN-based Real-time Food-to-Food Translation
Kizashi Nakano*, Daichi Horita*, Nobuchika Sakata, Kiyoshi Kiyokawa, Keiji Yanai, and Takuji Narumi (*) equally contributed
In IEEE VR, poster, 2019.
[Paper] [Video]

[4] Real-Time Image Classification and Transformation Apps on iOS by “Chainer2MPSNNGraph”
Yuki Izumi, Daichi Horita, Ryosuke Tanno, and Keiji Yanai
In NeurIPS Workshop, 2018.
[Paper]

[3] Ramen Spoon Eraser: CNN-based Photo Transformation for Improving Attractiveness of Ramen Photos
Daichi Horita, Jaehyeong Cho, Takumi Ege, and Keiji Yanai
In VRST, poster, 2018.
[Paper]

[2] Magical Rice Bowl: Real-time Food Category Changer
Ryosuke Tanno, Daichi Horita, Wataru Shimoda, and Keiji Yanai
In ACM Multimedia, demo, 2018.
[Paper]

[1] Food Category Transfer with Conditional Cycle GAN and a Large-scale Food Image Dataset
Daichi Horita, Ryosuke Tanno, Wataru Shimoda, and Keiji Yanai
In IJCAI Workshop, oral, 2018.
[Paper]

Scholarship & Grant

Erasmus+ ICM.
€6600 (1,000,000 JPY)
Jan 2023 - Jun 2023
[Webpage]

Microsoft Research Asia Collaborative Research 2022 Grant (D-CORE) Award.
1,000,000 JPY ($7,200)
April 2022

Japan Society for the Promotion of Scienece (JSPS) Research Fellowship for Young Scientists (DC1)
3,400,000 JPY ($30,000) per year
April 2022 - March 2025

Toyota and Dwango AI Scholarship.
2,400,000 JPY ($20,000)
April 2020 - March 2022

IPA, MITOU.
2,400,000 JPY ($20,000)
with Kizashi Nakano and Prof. Masahiko Inami
April 2019 - March 2020
[Webpage]

Award

Dean’s Award for Master Graduation Thesis in The University of Tokyo.
March 2022
[Webpage]

IPA MITO Super Creater.
May 2020
which is admired as an excellent creator by government of Japan.
[Webpage]

Dean's Award for Bachelor Graduation Thesis in The University of Electro-Communications.
March 2020

Student Award for Academic Achievement in The University of Electro-Communications.
March 2020

Student Award for Academic Achievement in The University of Electro-Communications.
March 2019

1st place at HackU hosted by Yahoo! JAPAN.
May 2017
[Webpage]

1st place at RoboCup Japan Open @Home Open Platform with team “kara@ge++”.
May 2017
[Webpage]

Media

NEWS ZERO よみうりテレビ.
テレビ出演
May 2019
[Webpage]

J-WAVE「STEP ONE」「炒飯のAR」を見て白米を食べると…炒飯の味に!?
ラジオ出演
April 2019
[Webpage]

発掘!イグ・ノーベル賞(37)電気通信大学 1杯のラーメンにかけるAI
新聞掲載
Dec 2018
[Webpage]

Reviewer Experience

IEEE Transactions on Multimedia, CVPR 2024.