RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images

GPS-Gaussian Ours Sparse input views TransHuman GT Fitted SMPL Vanilla 3DGS Figure 1 . High-fidelity human novel view synthesis. Given very sparse-view input images (e.g., 4 views) that do not enable accurate human template estimation due to the limited overlappings, our method can robustly synthesize high-fidelity novel views in a generalizable manner, without requiring any further fine-tuning or subject-specific optimization. Compared to both NeRF-based method, e.g., TransHuman [55], and 3D Gaussian Splatting (3DGS) based methods, e.g., vanilla 3DGS [30] and GPS-Gaussian [90], our approach produces better result.