MoNeRF: Deformable Neural Rendering for Talking Heads via Latent Motion Navigation

Abstract Novel view synthesis for talking heads presents significant challenges due to the complex and diverse motion transformations involved. Conventional methods often resort to reliance on structure priors, like facial templates, to warp observed images into a canonical space conducive to rendering. However, the incorporation of such priors introduces a trade‐off‐while aiding in synthesis, they concurrently amplify model complexity, limiting generalizability to other deformable scenes. Departing from this paradigm, we introduce a pioneering solution: the motion‐conditioned neural radiance field, MoNeRF, designed to model talking heads through latent motion navigation. At the core of MoNeRF lies a novel approach utilizing a compact set of latent codes to represent orthogonal motion directions. This innovative strategy empowers MoNeRF to efficiently capture and depict intricate scene motion by linearly combining these latent codes. In an extended capability, MoNeRF facilitates motion control through latent code adjustments, supports view transfer based on reference videos, and seamlessly extends its applicability to model human bodies without necessitating structural modifications. Rigorous quantitative and qualitative experiments unequivocally demonstrate MoNeRF's superior performance compared to state‐of‐the‐art methods in talking head synthesis. We will release the source code upon publication.