AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Pano-GS: Perception-Aware Gaussian Optimization with Gradient Consistency and Multi-Criteria Densification for High-Quality Rendering

Yang Deng, Zhanke Wang, Jiahao Wu, Jie Liang, Jingui Ma, Yang Hu, Ronggang Wang

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
add gradient consistency-constrained loss (ablation)Scaffold-GS · Tanks&TemplesPSNR: 24.05 -> 24.45Improved
add gradient consistency-constrained loss (ablation)Scaffold-GS · Tanks&TemplesLPIPS: 0.173 -> 0.151Improved
add multi-criteria densification only (ablation)Scaffold-GS · Tanks&TemplesLPIPS: 0.173 -> 0.146Improved
add stochastic perturbation exploration only (ablation)Scaffold-GS · Tanks&TemplesPSNR: 24.05 -> 24.20Improved
add MDS and SPE on top of GCL (ablation)Pano-GS · Tanks&TemplesPSNR: 24.45 -> 24.56Improved
add SPE to GCL+MDS (ablation)Pano-GS · Tanks&TemplesLPIPS: 0.137 -> 0.136No clear effect
Pano-GS vs Scaffold-GSScaffold-GS · Mip-NeRF 360PSNR: 27.59 -> 28.08Improved
Pano-GS vs Revised-GS/Pixel-GS SSIM3DGS baselines · Mip-NeRF 360SSIM: 0.823 -> 0.818Hurt
Pano-GS vs Pixel-GS LPIPSPixel-GS · Mip-NeRF 360LPIPS: 0.194 -> 0.194No clear effect
Pano-GS vs Pixel-GS model sizePixel-GS · Mip-NeRF 360model size: 1.24 GB -> 420 MBImproved
Pano-GS vs Scaffold-GS training time and sizeScaffold-GS · Mip-NeRF 360training time (min): 40 m -> 70 mHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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