Koki Nagano ![](/sites/default/files/person/DSC_5733-Edit_0.jpg) Koki Nagano is a principal research scientist at Nvidia Research. He works at the intersection of Graphics and AI with focus on achieving realistic digital humans using data-driven techniques and deep learning. He worked on a 3D display that allows an interactive conversation with a holographic projection of Holocaust survivors to preserve visual archives of the testimonies for future classrooms. His work on skin microgeometry synthesis has helped create digital characters in blockbuster movies such as “Ready Player One” and “Blade Runner 2049” as well as the open source ones such as “Digital Mike” and “Digital Emily 2.0”. His work on photorealistic human digitization has been shown in places including World Economic Forum, EmTech, TEDxCharlottesville, and SIGGRAPH Real-time Live!. His work has also led to the development of the state of the art Deepfake detection technology in collaboration with top media forensics experts. He obtained his PhD from the University of Southern California advised by Dr. Paul Debevec at USC ICT and his BE from the Tokyo Institute of Technology. Personal page: Research Area(s) [Artificial Intelligence and Machine Learning ](/index.php/research-area/machine-learning-artificial-intelligence) [Computer Graphics](/index.php/research-area/computer-graphics) [Computer Vision](/index.php/research-area/computer-vision) [Generative AI](/index.php/research-area/generative-ai) Main Field of Interest [Computer Graphics](/index.php/research-area/computer-graphics) Google Scholar [https://scholar.google.com/citations?user=GB7NfS4AAAAJ&hl=ja](https://scholar.google.com/citations?user=GB7NfS4AAAAJ&hl=ja) ### Publications ### 2025 [Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation](/index.php/publication/2025-11_seeing-what-matters-generalizable-ai-generated-video-detection-forensic) Riccardo Corvi, Davide Cozzolino, [Ekta Prashnani](/index.php/person/ekta-prashnani), [Shalini De Mello](/index.php/person/shalini-de-mello), [Koki Nagano](/index.php/person/koki-nagano), Luisa Verdoliva [Advances in Neural Information Processing Systems (NeurIPS) 2025](https://neurips.cc/virtual/2025/loc/san-diego/poster/117010) [GAIA: Generative Animatable Interactive Avatars with Expression-conditioned Gaussians](/publication/2025-08_gaia-generative-animatable-interactive-avatars-expression-conditioned-gaussians) Zhengming Yu, [Tianye Li](/person/tianye-li), Jingxiang Sun, [Omer Shapira](/person/omer-shapira), [Seonwook Park](/person/seonwook-park), [Michael Stengel](/person/michael-stengel), Matthew Chan, Xin Li, Wenping Wang, [Koki Nagano](/person/koki-nagano), [Shalini De Mello](/person/shalini-de-mello) [ACM SIGGRAPH 2025](https://dl.acm.org/doi/10.1145/3721238.3730737) [BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation](/publication/2025-06_blade-single-view-body-mesh-estimation-through-accurate-depth-estimation) Shengze Wang, [Jiefeng Li](/person/jiefeng-li), [Tianye Li](/person/tianye-li), [Ye Yuan](/person/ye-yuan), Henry Fuchs, [Koki Nagano](/person/koki-nagano), [Shalini De Mello](/person/shalini-de-mello), [Michael Stengel](/person/michael-stengel) [IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2025](https://openaccess.thecvf.com/content/CVPR2025/papers/Wang_BLADE_Single-view_Body_Mesh_Estimation_through_Accurate_Depth_Estimation_CVPR_2025_paper.pdf) [Coherent 3D Portrait Video Reconstruction via Triplane Fusion](/publication/2025-06_coherent-3d-portrait-video-reconstruction-triplane-fusion) Shengze Wang, [Xueting Li](/person/xueting-li), [Chao Liu](/person/chao-liu), Matthew Chan, [Michael Stengel](/person/michael-stengel), Henry Fuchs, [Shalini De Mello](/person/shalini-de-mello), [Koki Nagano](/person/koki-nagano) [IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2025](https://openaccess.thecvf.com/content/CVPR2025/papers/Wang_Coherent_3D_Portrait_Video_Reconstruction_via_Triplane_Fusion_CVPR_2025_paper.pdf) [AI 3D Selfie: Real-Time Single-Image 3D Face Reconstruction for Light-Field Displays](/publication/2025-05_ai-3d-selfie-real-time-single-image-3d-face-reconstruction-light-field-displays) [Jonghyun Kim](/person/jonghyun-kim), [Michael Stengel](/person/michael-stengel), Matthew Chan, [Koki Nagano](/person/koki-nagano), [Shalini De Mello](/person/shalini-de-mello), [David Luebke](/person/david-luebke) [The Society of Information Display (SID) 2025](https://sid.onlinelibrary.wiley.com/doi/abs/10.1002/sdtp.18377) ### 2024 [Avatar Fingerprinting for Authorized Use of Synthetic Talking-Head Videos](/index.php/publication/2024-09_avatar-fingerprinting-authorized-use-synthetic-talking-head-videos) [Ekta Prashnani](/index.php/person/ekta-prashnani), [Koki Nagano](/index.php/person/koki-nagano), [Shalini De Mello](/index.php/person/shalini-de-mello), [David Luebke](/index.php/person/david-luebke), Orazio Gallo [European Conference on Computer Vision (ECCV) 2024](https://eccv.ecva.net) [Dream-in-4D: A Unified Approach for Text- and Image-guided 4D Scene Generation](/publication/2024-06_dream-4d-unified-approach-text-and-image-guided-4d-scene-generation) Yufeng Zheng, [Xueting Li](/person/xueting-li), [Koki Nagano](/person/koki-nagano), [Sifei Liu](/person/sifei-liu), Otmar Hilliges, [Shalini De Mello](/person/shalini-de-mello) [IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2024](https://openaccess.thecvf.com/content/CVPR2024/papers/Zheng_A_Unified_Approach_for_Text-_and_Image-guided_4D_Scene_Generation_CVPR_2024_paper.pdf) [GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning](/index.php/publication/2024-06_gavatar-animatable-3d-gaussian-avatars-implicit-mesh-learning) [Ye Yuan](/index.php/person/ye-yuan), [Xueting Li](/index.php/person/xueting-li), Yangyi Huang, [Shalini De Mello](/index.php/person/shalini-de-mello), [Koki Nagano](/index.php/person/koki-nagano), [Jan Kautz](/index.php/person/jan-kautz), [Umar Iqbal](/index.php/person/umar-iqbal) [IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2024](https://openaccess.thecvf.com/content/CVPR2024/papers/Yuan_GAvatar_Animatable_3D_Gaussian_Avatars_with_Implicit_Mesh_Learning_CVPR_2024_paper.pdf) Highlight [What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs](/publication/2024-06_what-you-see-what-you-gan-rendering-every-pixel-high-fidelity-geometry-3d-gans) [Alexander Trevithick](/person/alexander-trevithick), Matthew Chan, Towaki Takikawa, [Umar Iqbal](/person/umar-iqbal), [Shalini De Mello](/person/shalini-de-mello), Manmohan Chandraker, Ravi Ramamoorthi, [Koki Nagano](/person/koki-nagano) [IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2024](https://openaccess.thecvf.com/content/CVPR2024/papers/Trevithick_What_You_See_is_What_You_GAN_Rendering_Every_Pixel_CVPR_2024_paper.pdf) ### 2023 [Generalizable One-shot 3D Neural Head Avatar](/index.php/publication/2023-12_generalizable-one-shot-3d-neural-head-avatar) [Xueting Li](/index.php/person/xueting-li), [Shalini De Mello](/index.php/person/shalini-de-mello), [Sifei Liu](/index.php/person/sifei-liu), [Koki Nagano](/index.php/person/koki-nagano), [Umar Iqbal](/index.php/person/umar-iqbal), [Jan Kautz](/index.php/person/jan-kautz) [Advances in Neural Information Processing Systems (NeurIPS) 2023](https://neurips.cc/) [Generative Novel View Synthesis with 3D-Aware Diffusion Models](/publication/2023-10_generative-novel-view-synthesis-3d-aware-diffusion-models) Eric R. Chan, [Koki Nagano](/person/koki-nagano), Matthew Chan, Alexander W. Bergman, Jeong Joon Park, Axel Levy, [Miika Aittala](/person/miika-aittala), [Shalini De Mello](/person/shalini-de-mello), [Tero Karras](/person/tero-karras), Gordon Wetzstein [International Conference on Computer Vision (ICCV) 2023](https://iccv2023.thecvf.com/) Oral [AI-Mediated 3D Video Conferencing](/publication/2023-08_ai-mediated-3d-video-conferencing) [Michael Stengel](/person/michael-stengel), [Koki Nagano](/person/koki-nagano), [Chao Liu](/person/chao-liu), Matthew Chan, Alex Trevithick, [Shalini De Mello](/person/shalini-de-mello), [Jonghyun Kim](/person/jonghyun-kim), [David Luebke](/person/david-luebke), [Amrita Mazumdar](/person/amrita-mazumdar), Shengze Wang, Mayoore Jaiswal [ACM SIGGRAPH Emerging Technologies 2023](https://dl.acm.org/doi/abs/10.1145/3588037.3595385) [Live 3D Portrait: Real-Time Radiance Fields for Single-Image Portrait View Synthesis](/publication/2023-08_live-3d-portrait-real-time-radiance-fields-single-image-portrait-view-synthesis) Alexander Trevithick, Matthew Chan, [Michael Stengel](/person/michael-stengel), Eric R. Chan, [Chao Liu](/person/chao-liu), [Zhiding Yu](/person/zhiding-yu), Sameh Khamis, Manmohan Chandraker, Ravi Ramamoorthi, [Koki Nagano](/person/koki-nagano) [ACM Transactions On Graphics (SIGGRAPH 2023)](https://s2023.siggraph.org/) [SSIF: Single-shot Implicit Morphable Faces With Consistent Texture Parameterization](/index.php/publication/2023-08_ssif-single-shot-implicit-morphable-faces-consistent-texture-parameterization) Connor Zhizhen Lin, [Koki Nagano](/index.php/person/koki-nagano), [Jan Kautz](/index.php/person/jan-kautz), Eric R. Chan, [Umar Iqbal](/index.php/person/umar-iqbal), Leonidas Guibas, Gordon Wetzstein, Sameh Khamis [SIGGRAPH 2023](https://s2023.siggraph.org/) ### 2022 [Efficient Geometry-aware 3D Generative Adversarial Networks](/publication/2022-06_efficient-geometry-aware-3d-generative-adversarial-networks) Eric R. Chan, Connor Z. Lin, Matthew A. Chan, [Koki Nagano](/person/koki-nagano), Boxiao Pan, [Shalini De Mello](/person/shalini-de-mello), Orazio Gallo, Leonidas Guibas, [Jonathan Tremblay](/person/jonathan-tremblay), Sameh Khamis, [Tero Karras](/person/tero-karras), Gordon Wetzstein [IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022](https://cvpr2022.thecvf.com/) Oral [RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis ](/publication/2022-01_rtmv-ray-traced-multi-view-synthetic-dataset-novel-view-synthesis) [Jonathan Tremblay](/person/jonathan-tremblay), Moustafa Meshry, [Stan Birchfield](/person/stan-birchfield), Alex Evans, [Jan Kautz](/person/jan-kautz), [Alex Keller](/person/alex-keller), Sameh Khamis, [Charles Loop](/person/charles-loop), Nate Morrical, [Thomas Müller](/person/thomas-muller), [Koki Nagano](/person/koki-nagano), Towaki Takikawa, [Stan Birchfield](/person/stan-birchfield) [ECCV 2022 Workshop on Learning to Generate 3D Shapes and Scenes](https://learn3dg.github.io/)