AI Paper Atlas

Research map / 3D vision / Gaussian splatting

SmartSplat: Feature-Smart Gaussians for Scalable Compression of Ultra-High-Resolution Images

Linfei Li, Lin Zhang, Zhong Wang, Ying Shen

AAAI 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 1 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
SmartSplat feature-aware sampling vs 3DGS at same CRSmartSplat · DIV8KPSNR: 1.53 dB PSNR gain over 3DGSImproved
SmartSplat vs GI (RS), CR 20SmartSplat · DIV8KPSNR: 30.45 -> 33.26Improved
SmartSplat vs ImageGS at CR 200SmartSplat · DIV8K (CR 200)PSNR: 26.80 vs 25.75Hurt
SmartSplat vs ImageGS at CR 20-100SmartSplat · DIV8KPSNR: 32.00 -> 33.26 (CR 20)Improved
SmartSplat vs GI (RS) on 16KSmartSplat · DIV16KPSNR: about 5.64 dB gainImproved
SmartSplat still trains at extreme CR where GI and ImageGS failSmartSplat · DIV16K (CR 3000)PSNR: 24.72 (baselines Fail/OOM)Improved
train SmartSplat for only 1K instead of 10K iterations (ablation)SmartSplat · 10848x16320 image, CR 200PSNR: 31.87 -> 30.52Mixed
SmartSplat 1K iterations vs GI 10K iterationsSmartSplat · 10848x16320 image, CR 200PSNR: 19.86 -> 30.52Improved
SmartSplat vs 3DGS memory and timeSmartSplat · 10848x16320 image, CR 200training time (s): 7841.80 -> 2237.52Improved

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