arXiv Computer Vision By Ge Gao, Siyue Teng, Chanqgi Wang, Fan Zhang, Nantheera Anantrasirichai, Jui Chiu Chiang, Wen-Hsiao Peng, David Bull

Gaussian Splatting-based Volumetric Video Compression with Sparse 4D Anchors

Read the original on arXiv Computer Vision →

The paper introduces SAGA, a volumetric video codec that uses sparse 4D anchors to guide Gaussian splatting for dynamic scene representation. By hierarchically arranging anchors and employing coordinate‑based INR decoders, SAGA shares geometry and appearance across primitives, captures long‑range dependencies with an orthogonality‑informed slot‑update strategy, and achieves substantial BD‑rate reductions on the Neu3D test set.

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.