AI RESEARCH

SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis

arXiv CS.CV

ArXi:2605.07287v1 Announce Type: new Generalizable novel view synthesis aims to render unseen views from uncalibrated input images without requiring per-scene optimization. Recent feed-forward approaches based on 3D Gaussian Splatting have achieved promising efficiency and rendering quality. However, most of them assign a fixed number of Gaussians to each pixel or voxel, ignoring the spatially varying complexity of real-world scenes.