AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Direct Conditional Parameterization for N-Dimensional Splatting

Zhongpai Gao, Benjamin Planche, Van N Nguyen, Meng Zheng, Anwesa Choudhuri, Arun Innanje, Terrence Chen, Ziyan Wu

NeurIPS 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes Direct Conditional Parameterization for N-dimensional Gaussian splatting (N-DGS), which conditions lifted joint Gaussians over position and conditioning variables (view, time) to get view- and time-dependent primitives.

Problem

Modeling view-dependent and dynamic appearance with Gaussian splatting by conditioning primitives on variables such as view direction and time, where the abstract indicates the prior lifted-distribution formulation is the setting being improved.

Approach

Each primitive is lifted into a joint Gaussian over 3D position and conditioning variables and conditionally sliced at render time, so mean, opacity and covariance vary continuously with view or time; the title suggests the conditional parameterization is defined directly rather than via a separate slicing step (details not in the abstract).

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace covariance-derived conditioning with direct conditional parameterization (Gaussian)N-DGS · Mip-NeRF 360 (MCMC)PSNR (dB): 26.88 -> 27.67Improved
replace covariance-derived conditioning with direct conditional parameterization (Gaussian)N-DGS · D-NeRF (MCMC)PSNR (dB): 34.63 -> 34.64No clear effect
replace covariance-derived conditioning with direct conditional parameterization (Beta)UBS · 7DGS-PBR (MCMC)PSNR (dB): 30.61 -> 31.87Improved
replace covariance-derived conditioning with direct conditional parameterization (Beta)UBS · NeRF Synthetic (MCMC)PSNR (dB): 34.48 -> 34.53No clear effect
direct conditioning with fused CUDA slicingN-DGS/UBS · Slicing time, 1M primitivesms: 0.71 -> 0.10 (C=3)Improved
add learned per-dimension coupling Lambda instead of fixed Lambda=0 (ablation)dGS · 6DGS-PBRPSNR (dB): 36.54 -> 37.75Improved
add learned per-dimension coupling Lambda instead of fixed Lambda=1 (ablation)dGS · 6DGS-PBRPSNR (dB): 37.31 -> 37.75Improved
add learned Lambda instead of fixed Lambda=0 (ablation)dGS · NeRF SyntheticPSNR (dB): 33.84 -> 33.91Improved
add spatial scaling s-bar on the coupling factor (ablation)dGS · NeRF SyntheticPSNR (dB): 31.26 -> 33.91Improved
add spatial scaling s-bar on the coupling factor (ablation)dGS · 6DGS-PBRPSNR (dB): 34.78 -> 37.75Improved
use structured factorized regression instead of unrestricted direct regression (ablation)dGS · NeRF SyntheticPSNR (dB): 32.91 -> 33.91Improved
use full coupling (Lambda=1) instead of opacity-only (Lambda=0) (ablation)dGS · NeRF Synthetic vs 6DGS-PBRPSNR (dB): NeRF Synthetic 33.84 -> 33.78; 6DGS-PBR 36.54 -> 37.31Mixed

Experimental setup

Builds on: 3D Gaussian Splatting N-dimensional Gaussians

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