Coherent3D: Coherent 3D Portrait Video Reconstruction via Triplane Fusion
This addresses the challenge of democratized 3D telepresence by improving realism for users, though it is incremental as it builds on existing frameworks like 3D GANs and fusion techniques.
The paper tackles the problem of achieving both temporal consistency and faithful per-frame appearance in 3D portrait video reconstruction from single images, proposing a fusion-based method that combines canonical 3D priors with dynamic inputs to produce state-of-the-art results on in-studio and in-the-wild datasets.
Recent breakthroughs in single-image 3D portrait reconstruction have enabled telepresence systems to stream 3D portrait videos from a single camera in real-time, democratizing telepresence. However, per-frame 3D reconstruction exhibits temporal inconsistency and forgets the user's appearance. On the other hand, self-reenactment methods can render coherent 3D portraits by driving a 3D avatar built from a single reference image, but fail to faithfully preserve the user's per-frame appearance (e.g., instantaneous facial expression and lighting). As a result, none of these two frameworks is an ideal solution for democratized 3D telepresence. In this work, we address this dilemma and propose a novel solution that maintains both coherent identity and dynamic per-frame appearance to enable the best possible realism. To this end, we propose a new fusion-based method that takes the best of both worlds by fusing a canonical 3D prior from a reference view with dynamic appearance from per-frame input views, producing temporally stable 3D videos with faithful reconstruction of the user's per-frame appearance. Trained only using synthetic data produced by an expression-conditioned 3D GAN, our encoder-based method achieves both state-of-the-art 3D reconstruction and temporal consistency on in-studio and in-the-wild datasets. https://research.nvidia.com/labs/amri/projects/coherent3d