Efficient neural implicit representation for 3D human reconstruction

Zexu Huang, Sarah Monazam Erfani, Siying Lu, Mingming Gong

Abstract: Highlights•Generates high-quality, animatable human avatars from single-camera video in minutes.•Pre-trained model: Enhances human estimation in dynamic NeRF for better avatars.•Efficient rendering: Replaces standard NeRF with a SoTA model for faster training.•Posture-Sensitive Space Reduction: Balances rendering quality and efficiency.