Umar Iqbal

26

Papers

90

Total Citations

Papers (26)

GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning

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

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

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

PoseTrack: Joint Multi-Person Pose Estimation and Tracking

PoseTrack: A Benchmark for Human Pose Estimation and Tracking

Self-Supervised Viewpoint Learning From Image Collections

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

Learning to Track Instances without Video Annotations

Weakly-Supervised Physically Unconstrained Gaze Estimation

DexYCB: A Benchmark for Capturing Hand Grasping of Objects

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

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

Few-Shot Adaptive Gaze Estimation

Physics-Based Human Motion Estimation and Synthesis From Videos

Self-Supervised Object Detection via Generative Image Synthesis

RANA: Relightable Articulated Neural Avatars

PhysDiff: Physics-Guided Human Motion Diffusion Model

Learning Human Dynamics in Autonomous Driving Scenarios

Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints

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

SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing

GENMO: A GENeralist Model for Human MOtion

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

A Dual-Source Approach for 3D Pose Estimation From a Single Image

Generalizable One-shot 3D Neural Head Avatar