AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Learning Unified Representation of 3D Gaussian Splatting

Yuelin Xin, Yuheng Liu, Xiaohui Xie, Xinke Li

ICLR 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 3 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
encode Gaussians as submanifold fields instead of raw parametersVAE embedding · ShapeSplatPSNR: 37.512 -> 63.408Improved
encode Gaussians as submanifold fields instead of raw parametersVAE embedding · Mip-NeRF 360PSNR: 18.818 -> 29.833Improved
use SF-VAE point-cloud decoder with parametric input (ablation)parametric VAE · ShapeSplatPSNR: 37.512 -> 44.725Improved
use submanifold field input in addition to the SF decoder (ablation)VAE embedding · Mip-NeRF 360PSNR: 20.923 -> 29.833Improved
submanifold field representation under cross-domain transferSF-VAE · train ShapeSplat, test Mip-NeRF 360PSNR: 9.753 -> 19.194Improved
submanifold field instead of parametric (L1 distance)SF-VAE · ShapeSplatL1-Dist: 0.040 -> 0.098Hurt
increase sampled points P beyond 12^2 (ablation)SF-VAE · Mip-NeRF 360reconstruction qualityNo clear effect
replace PointNet encoder with DGCNN (ablation)SF-VAE · Mip-NeRF 360reconstruction fidelityNo clear effect
GPU FP32 fitting module instead of CPU FP64 (ablation)SF-VAE · Mip-NeRF 360PSNR: -0.4 PSNR, 85x speedupNo clear effect
use SF embedding as regression target for Gaussian Neural FieldGaussian Neural Field · visual fidelityrendering qualityImproved

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