Albert Pumarola

papers

2,645

total citations

papers (14)

Avatars Grow Legs: Generating Smooth Human Motion From Sparse Tracking Inputs With Diffusion Model

CVPR 2023arXiv

133

citations

H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction

ICCV 2021arXiv

104

citations

C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds

CVPR 2020arXiv

citations

Bespoke Solvers for Generative Flow Models

ICLR 2024arXiv

citations

Re-ReND: Real-Time Rendering of NeRFs across Devices

ICCV 2023arXiv

citations

VisCo Grids: Surface Reconstruction with Viscosity and Coarea Grids

NEURIPS 2022arXiv

citations

Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models

AAAI 2025arXiv

citations

Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models

ICML 2024arXiv

citations

FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute

CVPR 2025arXiv

citations

Autoregressive Distillation of Diffusion Transformers

CVPR 2025arXiv

citations

GanHand: Predicting Human Grasp Affordances in Multi-Object Scenes

CVPR 2020

citations

Albert Pumarola

papers (14)

D-NeRF: Neural Radiance Fields for Dynamic Scenes

SMPLicit: Topology-Aware Generative Model for Clothed People

Context-Aware Human Motion Prediction

Avatars Grow Legs: Generating Smooth Human Motion From Sparse Tracking Inputs With Diffusion Model

H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction

C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds

Bespoke Solvers for Generative Flow Models

Re-ReND: Real-Time Rendering of NeRFs across Devices

VisCo Grids: Surface Reconstruction with Viscosity and Coarea Grids

Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models

Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models

FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute

Autoregressive Distillation of Diffusion Transformers

GanHand: Predicting Human Grasp Affordances in Multi-Object Scenes

papers (14)

D-NeRF: Neural Radiance Fields for Dynamic Scenes

SMPLicit: Topology-Aware Generative Model for Clothed People

Context-Aware Human Motion Prediction

Avatars Grow Legs: Generating Smooth Human Motion From Sparse Tracking Inputs With Diffusion Model

H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction

C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds

Bespoke Solvers for Generative Flow Models

Re-ReND: Real-Time Rendering of NeRFs across Devices

VisCo Grids: Surface Reconstruction with Viscosity and Coarea Grids

Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models

Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models

FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute

Autoregressive Distillation of Diffusion Transformers

GanHand: Predicting Human Grasp Affordances in Multi-Object Scenes