Ryugo Morita

I am a second-year M.S. student in the Graduate School of Applied Informatics at Hosei University. Currently, I belong to the iMedia Lab led by Assoc. Prof. Jinjia Zhou, where I conduct research on layer-wise image generation and compression in generative models such as diffusion models and GANs. In addition to my work in computer vision, I also engage in HCI research focusing on AI-driven education, exploring how generative AI can enhance learning experiences and cognitive augmentation.

Google Scholar | Twitter | Github | LinkedIn

Research Experience

• SDS DFKI, Germany (Dec 2023 – Dec 2024)
  Advisor: Prof. Andreas Dengel
  • Training-free Chroma Key Content Generation Diffusion Model (CVPR2025)
  • Edge-based Denoising Image Compression (EUSIPCO2024)
  • GenAIReading (AHs2025)
• iMedia Lab, Hosei University (Apr 2021 – Present)
  Advisor: Assoc. Prof. Jinjia Zhou
  • Text-Guided Image Manipulation (WACV2023)
  • Background-aware text-to-image synthesis (ICIP2023)
  • Background Interpretation-based Foreground Image Synthesize (MIRU2023)

Internship Experiences

• SB intuitions (Mar 2024 – present): Flux model for image editing
• EQUES (Dec 2023 – present): Research leader for anime generation
• Matsuo Institute (Oct 2023 – present): Diffusion model for inpainting with Panasonic
• DFKI, Germany (Dec 2023 – Dec 2024): Diffusion model research
• CyberAgent, Inc. (Jan 2023 – Dec 2024): Web advertising images generation
• Olympic Broadcasting Services (Paris2024): Video editing and translation
• KDDI Research, Inc. (Dec 2023 – Mar 2024): Edge-based Denoising Image Compression
• DeNA, Inc. (Aug 2023 – Sep 2023): Baseball data analysis
• Research Center at Hosei University (Aug 2022 – Dec 2023): Emotion analysis in online classes
• Smart Trade, Inc. (Aug 2021 – May 2022): Stock price prediction with GAN/LSTM
• Olympic Broadcasting Services (Tokyo2020): Video editing and translation

Publications

• [1] SAWNA: Space-Aware Text to Image Generation
  Ryugo Morita, Sho Kuno, Ryunosuke Tanaka, Rongzhi Li, Hoang Dai Dinh, Issey Sukeda
  SIGGRAPH2025 Poster
• [2] TKG-DM: Training-free Chroma Key Content Generation Diffusion Model
  Ryugo Morita, Stanislav Frolov, Brian Bernhard Moser, Takahiro Shirakawa, Ko Watanabe, Andreas Dengel and Jinjia Zhou
  CVPR 2025 Highlights (Top 13.5%) [Project Page] [Paper]
  
• [3] Bidirectional Learned Facial Animation Codec for Low Bitrate Talking Head Videos
  Riku Takahashi, Ryugo Morita, Fuma Kimishima, Kosuke Iwama and Jinjia Zhou
  DCC 2025 [Paper]
  
• [4] GenAIReading: Augmenting Human Cognition with Interactive Digital Textbooks Using Large Language Models and Image Generation Models
  Ryugo Morita, Ko Watanabe, Jinjia Zhou, Andreas Dengel, Shoya Ishimaru
  AHs 2025 [Paper]
  
• [5] Edge-based Denoising Image Compression
  Ryugo Morita, Hitoshi Nishimura, Ko Watanabe, Andreas Dengel and Jinjia Zhou
  EUSIPCO 2024 [Paper]
  
• [6] Learned Measurement Interpolation for Scalable Compressive Sensing
  Manato Shirai, Fuma Kimishima, Jinjia Zhou, Ryugo Morita
  IJCNN 2024 [Paper]
  
• [7] Visual question answering based evaluation metrics for text-to-image generation
  Mizuki Miyamoto, Ryugo Morita, Jinjia Zhou
  ISCAS 2023 [Paper]
  
• [8] Block based Adaptive Compressive Sensing with Sampling Rate Control
  Kosuke Iwama, Ryugo Morita, Jinjia Zhou
  ACMM Asia 2023 [Paper]
  
• [9] Dynamic Unilateral Dual Learning for Text to Image Synthesis
  Zhiqiang Zhang, Jiayao Xu, Ryugo Morita, Wenxin Yu, Jinjia Zhou
  ICIP 2023 [Paper]
  
• [10] Batinet: Background-aware Text to Image Synthesis and Manipulation Network
  Ryugo Morita, Zhiqiang Zhang, Jinjia Zhou
  ICIP 2023 [Paper]
  
• [11] Interactive Image Manipulation with Complex Text Instructions
  Ryugo Morita, Zhiqiang Zhang, Man M. Ho, Jinjia Zhou
  WACV 2023 [Paper]