Fictionarry

ER-NeRF. [ICCV'23] Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis

TalkingGaussian. [ECCV'24] TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting

DNGaussian. [CVPR'24] DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization

GeoSVR. [NeurIPS'25 Spotlight] GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction

InsTaG. [CVPR'25] InsTaG: Learning Personalized 3D Talking Head from Few-Second Video

AmbiSuR. [ICML'26] Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction