AI Paper Atlas

Research map / 3D vision / Gaussian splatting

GaussianImage++: Boosted Image Representation and Compression with 2D Gaussian Splatting

Tiantian Li, Xinjie Zhang, Xingtong Ge, Tongda Xu, Dailan He, Jun Zhang, Yan Wang

AAAI 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 4 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 growing and pruning densification (ablation)GaussianImage (5k GS) · KodakPSNR: 29.85 -> 31.75Improved
add growing only (ablation)no densification · Kodak (5k GS)PSNR: 29.85 -> 31.71Improved
add pruning only (ablation)no densification · Kodak (5k GS)PSNR: 29.85 -> 29.89No clear effect
add densification (ablation)GaussianImage++ · Kodak (5k GS)encode time (s): 102.78 -> 118.52Hurt
use LSQ+ instead of FP16 for position (ablation)GaussianImage++ quantization · KodakBD-Rate (%): 25.11 -> 0Improved
use LSQ+ instead of RVQ for color (ablation)GaussianImage++ quantization · KodakBD-Rate (%): 147.24 -> 0Improved
use bit-depth 12/10/6 instead of 12/8/8 (ablation)GaussianImage++ · KodakBD-Rate (%): 29.42 -> 0Improved
use bit-depth 12/10/6 instead of 16/10/6 (ablation)GaussianImage++ · KodakBD-Rate (%): 9.68 -> 0Improved
use smaller pruning/growing steps tp=100, tg=5000 instead of 500/10000 (ablation)GaussianImage++ densification · KodakPSNR: 31.56 -> 31.83Improved
replace GaussianImage with GaussianImage++GaussianImage · Kodak (10k GS)PSNR: 32.48 -> 35.41Improved
replace GaussianImage with GaussianImage++GaussianImage · DIV2K (10k GS)PSNR: 26.54 -> 28.14Improved
replace GaussianImage with GaussianImage++GaussianImage · Kodak (5k GS)MS-SSIM: 0.962 -> 0.960No clear effect

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