arXiv cs.CV
· Papers
Learning Stable Canonical Worlds for Novel View Synthesis and Beyond
arXiv:2606.23027v2 Announce Type: replace Abstract: Feed-forward Gaussian splatting (FFGS) facilitates real-time novel view synthesis, yet current methods often remain tied to view-dependent predictions. As more input views are added, they may accumulate noisy or redundant evidence instead of converging to a stable sce