Diff3R: Feed-forward 3D Gaussian Splatting with Uncertainty-aware Differentiable Optimization

Yueh-Cheng Liu, Jozef Hladký, Matthias Nießner +1

Recent advances in 3D Gaussian Splatting (3DGS) present two main directions: feed-forward models offer fast inference in sparse-view settings, while per-scene optimization yields h…