AI RESEARCH
Diff3R: Feed-forward 3D Gaussian Splatting with Uncertainty-aware Differentiable Optimization
arXiv CS.CV
•
ArXi:2604.01030v1 Announce Type: new 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 high-quality renderings but is computationally expensive. To combine the benefits of both, we