AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Complexity-guided Regularization for Generalizable Human Gaussian Splatting

Gun Ryu, Gi-Mun Um, Won-Sik Cheong, Wonjun Kim

NeurIPS 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 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 complexity-guided regularization for generalizable human Gaussian splatting so that Gaussian density adapts to geometric and textural complexity of human subjects, to better capture fine details in novel-view synthesis of unseen humans.

Problem

Generalizable human Gaussian splatting methods struggle to represent fine-grained details of human subjects because they impose no constraint on how densely Gaussians are allocated relative to local geometric and textural complexity.

Approach

Regularizes Gaussian density according to the complexity of the human body region (geometric and textural), so that complex regions receive denser Gaussians; based only on the abstract, the specific mechanism is not described.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add complexity-guided regularization (ablation)generalizable human Gaussian splatting · THuman2.0PSNR: 30.32 -> 30.79Improved
add complexity-aware patch-based supervision (ablation)generalizable human Gaussian splatting · THuman2.0PSNR: 30.32 -> 32.06Improved
combine regularization and patch supervision (ablation)generalizable human Gaussian splatting · THuman2.0PSNR: 32.06 -> 32.42Improved
add complexity-guided regularization (no depth loss) (ablation)generalizable human Gaussian splatting · THuman2.0 (without depth regularization)PSNR: 29.80 -> 30.41Improved
use complexity-aware patch sampling instead of random sampling (ablation)patch-based supervision · THuman2.0PSNR: 31.63 -> 32.06Improved
use image-gradient sampling instead of random sampling (ablation)patch-based supervision · THuman2.0PSNR: 31.63 -> 31.81Improved
use max of geometric and textural complexity instead of either alone (ablation)complexity prior · THuman2.0PSNR: 31.65 -> 32.42Improved
use max instead of mean to combine complexities (ablation)complexity prior · THuman2.0PSNR: 32.31 -> 32.42Improved
use pairwise ranking instead of Pearson correlation regularization (ablation)complexity-guided regularization · THuman2.0PSNR: 30.31 -> 30.79Improved
increase nearest neighbors k from 7 to 9 (ablation)density score · THuman2.0PSNR: 30.79 -> 30.75No clear effect
increase nearest neighbors k from 3 to 7 (ablation)density score · THuman2.0PSNR: 30.55 -> 30.79Improved
add complexity-guided regularization (ablation)Gaussian density · THuman2.0Spearman correlation: 0.1086 -> 0.4262Improved

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