Shunsuke Saito

papers

2,392

total citations

papers (29)

PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization

CVPR 2020arXiv

829

citations

KeypointNeRF: Generalizing Image-Based Volumetric Avatars Using Relative Spatial Encoding of Keypoints

ECCV 2022arXiv

102

citations

SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements

CVPR 2021arXiv

102

citations

COAP: Compositional Articulated Occupancy of People

CVPR 2022arXiv

citations

3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion

CVPR 2025arXiv

citations

Pixel-Aligned Volumetric Avatars

CVPR 2021arXiv

citations

Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images

ECCV 2022arXiv

citations

A Dataset of Relighted 3D Interacting Hands

NEURIPS 2023arXiv

citations

InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion

CVPR 2024arXiv

citations

GALA: Generating Animatable Layered Assets from a Single Scan

CVPR 2024arXiv

citations

Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars

ICCV 2025arXiv

citations

MEGANE: Morphable Eyeglass and Avatar Network

CVPR 2023arXiv

citations

RelightableHands: Efficient Neural Relighting of Articulated Hand Models

CVPR 2023arXiv

citations

Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior

CVPR 2025arXiv

citations

URHand: Universal Relightable Hands

CVPR 2024arXiv

citations

NCHO: Unsupervised Learning for Neural 3D Composition of Humans and Objects

ICCV 2023arXiv

citations

Pippo: High-Resolution Multi-View Humans from a Single Image

CVPR 2025arXiv

citations

REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning

CVPR 2025arXiv

citations

AutoAvatar: Autoregressive Neural Fields for Dynamic Avatar Modeling

ECCV 2022arXiv

citations

FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images

CVPR 2025arXiv

citations

ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling

ICCV 2025arXiv

citations

HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars

ICCV 2025arXiv

citations

PGC: Physics-Based Gaussian Cloth from a Single Pose

CVPR 2025arXiv

citations

Generative Modeling of Shape-Dependent Self-Contact Human Poses

ICCV 2025arXiv

citations

Shunsuke Saito

papers (29)

PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization

SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks

ARCH++: Animation-Ready Clothed Human Reconstruction Revisited

Sapiens: Foundation for Human Vision Models

Relightable Gaussian Codec Avatars

Monocular Real-Time Volumetric Performance Capture

KeypointNeRF: Generalizing Image-Based Volumetric Avatars Using Relative Spatial Encoding of Keypoints

SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements

COAP: Compositional Articulated Occupancy of People

3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion

Pixel-Aligned Volumetric Avatars

Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images

A Dataset of Relighted 3D Interacting Hands

InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion

GALA: Generating Animatable Layered Assets from a Single Scan

Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars

MEGANE: Morphable Eyeglass and Avatar Network

RelightableHands: Efficient Neural Relighting of Articulated Hand Models

Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior

URHand: Universal Relightable Hands

NCHO: Unsupervised Learning for Neural 3D Composition of Humans and Objects

Pippo: High-Resolution Multi-View Humans from a Single Image

REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning

AutoAvatar: Autoregressive Neural Fields for Dynamic Avatar Modeling

FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images

ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling

HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars

PGC: Physics-Based Gaussian Cloth from a Single Pose

Generative Modeling of Shape-Dependent Self-Contact Human Poses

papers (29)

PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization

SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks

ARCH++: Animation-Ready Clothed Human Reconstruction Revisited

Sapiens: Foundation for Human Vision Models

Relightable Gaussian Codec Avatars

Monocular Real-Time Volumetric Performance Capture

KeypointNeRF: Generalizing Image-Based Volumetric Avatars Using Relative Spatial Encoding of Keypoints

SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements

COAP: Compositional Articulated Occupancy of People

3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion

Pixel-Aligned Volumetric Avatars

Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images

A Dataset of Relighted 3D Interacting Hands

InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion

GALA: Generating Animatable Layered Assets from a Single Scan

Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars

MEGANE: Morphable Eyeglass and Avatar Network

RelightableHands: Efficient Neural Relighting of Articulated Hand Models

Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior

URHand: Universal Relightable Hands

NCHO: Unsupervised Learning for Neural 3D Composition of Humans and Objects

Pippo: High-Resolution Multi-View Humans from a Single Image

REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning

AutoAvatar: Autoregressive Neural Fields for Dynamic Avatar Modeling

FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images

ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling

HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars

PGC: Physics-Based Gaussian Cloth from a Single Pose

Generative Modeling of Shape-Dependent Self-Contact Human Poses