AI Paper Atlas

Research map / 3D vision / Gaussian splatting

HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression

Yihang Chen, Qianyi Wu, Weiyao Lin, Mehrtash Harandi, Jianfei Cai

ECCV 2024 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 167 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add hash-grid context model for anchor attribute entropy codingScaffold-GS · Mip-NeRF360size (MB): 253.9 -> 15.26 (lowrate), PSNR 27.50 -> 27.53Improved
replace anchor features with hash features directly (ablation)Scaffold-GS · Synthetic-NeRFfidelity / training stability / FPSHurt
binarize anchor attributes instead of rounding with noise-based quantization (ablation)HAC · anchor attributesinformation preservationHurt
add mutual-information context from hash grid (vs all-zero hash grid) (ablation)HAC · BungeeNeRF and Synthetic-NeRFbit rateImproved
add adaptive quantization module (AQM) (ablation)HAC · BungeeNeRF and Synthetic-NeRFfidelityImproved
add adaptive offset masking (ablation)HAC · BungeeNeRF and Synthetic-NeRFbit rateImproved
apply HAC instead of Morgenstern et al. dimension collapsing3DGS compression · Synthetic-NeRFPSNR: 31.05 -> 33.24 (lowrate); size 2.20 -> 1.18Improved
increase anchor feature dimension to 50 and add entropy loss regularizationHAC · Mip-NeRF360PSNR: 27.50 -> 27.77 (highrate vs Scaffold-GS)Improved
add HAC context models on training costScaffold-GS · BungeeNeRFtraining time (min): 15.1 -> 27.6Hurt
HAC pruning of invalid anchors on rendering speedScaffold-GS · BungeeNeRFFPS: 232 -> 283Improved
HAC versus Scaffold-GS on Synthetic-NeRF rendering speedScaffold-GS · Synthetic-NeRFFPS: 326 -> 341 (HAC); 3DGS 401Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy