We propose a novel 3D-aware diffusion-based method for generating photorealistic talking head videos directly from a single identity image and explicit control signals (e.g., expressions). Our method generates Multiplane Images (MPIs) that ensure geometric consistency, making them ideal for immersive viewing experiences like binocular videos for VR headsets. Unlike existing methods that often require a separate stage or joint optimization to reconstruct a 3D representation (such as NeRF or 3D Gaussians), our approach directly generates the final output through a single denoising process, eliminating the need for post-processing steps to render novel views efficiently. To effectively learn from monocular videos, we introduce a training mechanism that reconstructs the output MPI randomly in either the target or the reference camera space. This approach enables the model to simultaneously learn sharp image details and underlying 3D information. Extensive experiments demonstrate the effectiveness of our method, which achieves competitive avatar quality and novel-view rendering capabilities, even without explicit 3D reconstruction or high-quality multi-view training data.
View on arXiv@article{li2025_2504.19165,
title={ IM-Portrait: Learning 3D-aware Video Diffusion for Photorealistic Talking Heads from Monocular Videos },
author={ Yuan Li and Ziqian Bai and Feitong Tan and Zhaopeng Cui and Sean Fanello and Yinda Zhang },
journal={arXiv preprint arXiv:2504.19165},
year={ 2025 }
}