Rethinking 3D Noise: Learning 3D-Aware Video Priors via Optimization-Free Morphological Perturbations
Read the original on arXiv Computer Vision →The paper introduces 3D Morphological Perturbations, an optimization‑free regularizer for 3D representations such as NeRF and 3D Gaussian Splatting. By treating each Gaussian as a pixel‑like element, the method applies scale, rotation, and pruning perturbations to preserve spatial consistency across views, eliminating the need for per‑scene optimization during dataset curation. Experiments on a lightweight video diffusion sandbox and a 14B‑parameter video model show that the approach improves geometric priors, reduces mean depth error by 12.5% over state‑of‑the‑art 3D artifact refiners, and boosts downstream robotics policy success rates by up to 8.0% on three manipulation tasks.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.