arXiv Computer Vision
RacerGS: Residual-Autoregressive Context for 3D Gaussian Splatting Compression
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 22
Compressing 3D Gaussian Splatting via Cross-Representation Priors
arXiv:2609.23005v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) enables high-quality novel view synthesis but incurs high storage and transmission costs due to dense Gaussian primitives....
arXiv Computer Vision
Sep 22
LG-HCC: Local Geometry-Aware Hierarchical Context Compression for 3D Gaussian Splatting
arXiv:2603.28431v4 Announce Type: replace Abstract: Although 3D Gaussian Splatting (3DGS) enables high-fidelity real-time rendering, its prohibitive storage overhead severely hinders practical deploy...
arXiv Computer Vision
Sep 25
Towards Practical Compression of 3D Gaussian Splatting
The paper introduces COSA-GS, a new compression method for 3D Gaussian Splatting that avoids spatial aggregation by using anchor-wise causal factorization. It builds a compact learnable anchor latent from geometry context and fuses it with the geometry context to create an anchor context for attribute coding, employing only linear transformations and activations. The method is trained with rate–distortion optimization, adaptive Gaussian pruning, and quantization-aware training to ensure bit‑exact entropy decoding across platforms, achieving state‑of‑the‑art compression performance with fast, consistent cross‑platform decoding.
arXiv Computer Vision
4d ago
Gaussian Splatting-based Volumetric Video Compression with Sparse 4D Anchors
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.
arXiv Computer Vision
Oct 19
CodecSplat: Ultra-Compact Latent Coding for Feed-Forward 3D Gaussian Splatting
arXiv:2605.25563v2 Announce Type: replace Abstract: While feed-forward 3D Gaussian splatting reconstructs renderable Gaussian primitives from sparse context views without per-scene optimization, exis...
arXiv Computer Vision
Oct 15
Feed-Forward Multi-View Feature Coding for 3D Gaussian Splatting
arXiv:2610.20590v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting (3DGS) methods enable efficient reconstruction of 3D scenes from sparse multi-view images in a single forward pass,...