arXiv Computer Vision
LG-HCC: Local Geometry-Aware Hierarchical Context Compression for 3D Gaussian Splatting
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 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
Nov 2
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 27
RacerGS: Residual-Autoregressive Context for 3D Gaussian Splatting Compression
arXiv:2610.34263v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged as a promising approach for fast, high-quality novel-view rendering. However, its large parameter size remains...
arXiv Computer Vision
Oct 22
Unfolding 3D Gaussian Splatting via Iterative Gaussian Synopsis
The paper introduces Iterative Gaussian Synopsis, a top‑down unfolding framework that generates compact, progressive levels of detail for 3D Gaussian Splatting (3DGS). Starting from a full‑resolution 3DGS model, it iteratively prunes Gaussian primitives using a learnable mask, building a multi‑level hierarchy that preserves visual quality while reducing storage. The method combines hierarchical spatial grids with a shared Anchor Codebook to capture global structure and local details, enabling efficient, level‑specific rendering with minimal data overhead.
arXiv Computer Vision
Oct 16
Anchor3DGS: Feed-Forward 3D Gaussian Splatting with Compact Anchor-Based Representation
Anchor3DGS introduces a pose‑free, feed‑forward 3D Gaussian Splatting framework that replaces pixel‑aligned Gaussian prediction with a compact anchor‑based representation. By placing 3D anchors guided by information entropy, the method concentrates primitives in visually complex regions while ensuring broad spatial coverage, and each anchor aggregates multi‑view features to generate local Gaussians. A lightweight feature enhancement module refines the coarse RGB output, resulting in state‑of‑the‑art novel view synthesis quality with an order of magnitude fewer Gaussian primitives than prior approaches.