CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models

This paper presents CAP4D, an approach that uses a morphable multi-view diffusion model to reconstruct photoreal 4D (dynamic 3D) portrait avatars from any number of reference images.

It demonstrates state-of-the-art performance for single-, few-, and multi-image 4D portrait avatar reconstruction and bridges the gap in visual fidelity between single-image and multi-view reconstruction techniques.

The method involves generating novel views from reference images and using 3D Gaussian splatting for real-time animation and rendering.