SOURCE-LINKED INTELLIGENCE

Rethinking 3D Noise: Learning 3D-Aware Video Priors via Optimization-Free Morphological Perturbations

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

3D scene representations like NeRF and 3D Gaussian Splatting (3DGS) suffer severe artifacts in sparse-view settings. Recent generative 3D artifact fixers attempt to address this, but rely on paired corrupted and clean renders requiring costly, per-scene reconstructions across varying view configurations. While 2D image augmentations act as instant regularizers, no explicit equivalents exist for 3D representations to preserve spatial consistency across views, an essential property for 3D-aware training. We propose 3D Morphological Perturbations as an optimization-free regularizer that preserves

Read original source ↗ Open in workspace

recordType

paper

region

Global