Umar Iqbal

Latest

• 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
• Generalizable One-shot 3D Neural Head Avatar
• Self-Supervised Object Detection via Generative Image Synthesis
• Learning to Track Instances without Video Annotations
• Weakly-Supervised Physically Unconstrained Gaze Estimation
• Self-Supervised Viewpoint Learning From Image Collections
• Few-Shot Adaptive Gaze Estimation