Umar Iqbal

papers

1,636

total citations

papers (22)

Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction

ECCV 2020arXiv

citations

Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects

CVPR 2022arXiv

citations

Weakly-Supervised Physically Unconstrained Gaze Estimation

CVPR 2021arXiv

citations

Self-Supervised Viewpoint Learning From Image Collections

CVPR 2020arXiv

citations

Learning to Track Instances without Video Annotations

CVPR 2021arXiv

citations

What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs

CVPR 2024arXiv

citations

RANA: Relightable Articulated Neural Avatars

ICCV 2023arXiv

citations

GENMO: A GENeralist Model for Human MOtion

ICCV 2025arXiv

citations

SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing

CVPR 2025arXiv

citations

HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View Synthesis

ICCV 2025arXiv

citations

Self-Supervised Object Detection via Generative Image Synthesis

ICCV 2021arXiv

citations

AdaHuman: Animatable Detailed 3D Human Generation with Compositional Multiview Diffusion

ICCV 2025arXiv

citations

Learning Human Dynamics in Autonomous Driving Scenarios

ICCV 2023

citations

GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion

ICCV 2025arXiv

citations

Generalizable One-shot 3D Neural Head Avatar

NEURIPS 2023

citations

Umar Iqbal

papers (22)

PhysDiff: Physics-Guided Human Motion Diffusion Model

DexYCB: A Benchmark for Capturing Hand Grasping of Objects

Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints

GLAMR: Global Occlusion-Aware Human Mesh Recovery With Dynamic Cameras

Weakly-Supervised 3D Human Pose Learning via Multi-View Images in the Wild

Physics-Based Human Motion Estimation and Synthesis From Videos

GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning

Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction

Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects

Weakly-Supervised Physically Unconstrained Gaze Estimation

Self-Supervised Viewpoint Learning From Image Collections

Learning to Track Instances without Video Annotations

What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs

RANA: Relightable Articulated Neural Avatars

GENMO: A GENeralist Model for Human MOtion

SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing

HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View Synthesis

Self-Supervised Object Detection via Generative Image Synthesis

AdaHuman: Animatable Detailed 3D Human Generation with Compositional Multiview Diffusion

Learning Human Dynamics in Autonomous Driving Scenarios

GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion

Generalizable One-shot 3D Neural Head Avatar

papers (22)

PhysDiff: Physics-Guided Human Motion Diffusion Model

DexYCB: A Benchmark for Capturing Hand Grasping of Objects

Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints

GLAMR: Global Occlusion-Aware Human Mesh Recovery With Dynamic Cameras

Weakly-Supervised 3D Human Pose Learning via Multi-View Images in the Wild

Physics-Based Human Motion Estimation and Synthesis From Videos

GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning

Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction

Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects

Weakly-Supervised Physically Unconstrained Gaze Estimation

Self-Supervised Viewpoint Learning From Image Collections

Learning to Track Instances without Video Annotations

What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs

RANA: Relightable Articulated Neural Avatars

GENMO: A GENeralist Model for Human MOtion

SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing

HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View Synthesis

Self-Supervised Object Detection via Generative Image Synthesis

AdaHuman: Animatable Detailed 3D Human Generation with Compositional Multiview Diffusion

Learning Human Dynamics in Autonomous Driving Scenarios

GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion

Generalizable One-shot 3D Neural Head Avatar