Shunsuke Saito

GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion Transformers CVPR 2026 Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining CVPR 2026 3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion CVPR 2025 Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos ICLR 2025 ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling ICCV 2025 Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars ICCV 2025 FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images CVPR 2025 Generative Modeling of Shape-Dependent Self-Contact Human Poses ICCV 2025 HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars ICCV 2025 PGC: Physics-Based Gaussian Cloth from a Single Pose CVPR 2025 Pippo: High-Resolution Multi-View Humans from a Single Image CVPR 2025 REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning CVPR 2025 Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior CVPR 2025 Bridging the Gap: Studio-like Avatar Creation from a Monocular Phone Capture ECCV 2024 Codec Avatar Studio: Paired Human Captures for Complete, Driveable, and Generalizable Avatars NeurIPS 2024 Expressive Whole-Body 3D Gaussian Avatar ECCV 2024 GALA: Generating Animatable Layered Assets from a Single Scan CVPR 2024 High-Fidelity Modeling of Generalizable Wrinkle Deformation ECCV 2024 InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion CVPR 2024 Relightable Gaussian Codec Avatars CVPR 2024 Sapiens: Foundation for Human Vision Models ECCV 2024 URHand: Universal Relightable Hands CVPR 2024 A Dataset of Relighted 3D Interacting Hands NeurIPS 2023 MEGANE: Morphable Eyeglass and Avatar Network CVPR 2023 NCHO: Unsupervised Learning for Neural 3D Composition of Humans and Objects ICCV 2023 RelightableHands: Efficient Neural Relighting of Articulated Hand Models CVPR 2023 AutoAvatar: Autoregressive Neural Fields for Dynamic Avatar Modeling ECCV 2022 COAP: Compositional Articulated Occupancy of People CVPR 2022 KeypointNeRF: Generalizing Image-Based Volumetric Avatars Using Relative Spatial Encoding of Keypoints ECCV 2022 Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images ECCV 2022 ARCH++: Animation-Ready Clothed Human Reconstruction Revisited ICCV 2021 Pixel-Aligned Volumetric Avatars CVPR 2021 SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements CVPR 2021 SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks CVPR 2021 Monocular Real-Time Volumetric Performance Capture ECCV 2020 PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization CVPR 2020 Learning to Infer Implicit Surfaces without 3D Supervision NeurIPS 2019 PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization ICCV 2019 SiCloPe: Silhouette-Based Clothed People CVPR 2019 Mesoscopic Facial Geometry Inference Using Deep Neural Networks CVPR 2018 Learning Dense Facial Correspondences in Unconstrained Images ICCV 2017 Photorealistic Facial Texture Inference Using Deep Neural Networks CVPR 2017 Realistic Dynamic Facial Textures From a Single Image Using GANs ICCV 2017