AI Paper Atlas

Research map / 3D vision / Gaussian splatting

ClusterSplat: Semantic Cluster Selection for 3D Visual Grounding in Gaussian Splatting

Jaesung Lee, Hyeontaek Hwang, Gabriel Manalu, Daeyoung 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 ClusterSplat, which selects semantic clusters of 3D Gaussians for referring-expression grounding in 3DGS instead of heuristic thresholding of primitive-level relevance scores.

Problem

3D visual grounding in 3D Gaussian Splatting must output both a 2D mask and a set of 3D Gaussians for a referring expression; prior methods use heuristic thresholds or top-ratio filtering on primitive relevance scores, which vary across scenes and prompts and make such heuristics unreliable.

Approach

Replaces per-primitive thresholding with selection over semantic clusters of Gaussians, so the target set is chosen at the cluster level rather than by a scene-specific cutoff on dense relevance scores.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace primitive-level top-ratio filtering with scene-adaptive cluster-level Top-1 selectionClusterSplat vs ReferSplat · ScanRefer 3DmIoU: 4.05 -> 23.33Improved
train ReferSplat with our loss (same supervision)ReferSplat · ScanRefer 2DmIoU: 31.30 -> 31.55No clear effect
use scene-adaptive clustering instead of fixed KMeans K=128 (ablation)ClusterSplat cluster candidates · ScanRefer 3D mIoUmIoU: 18.31 -> 23.33Improved
increase fixed KMeans K from 128 to 512 (ablation)fixed KMeans clusters · ScanRefer 3D mIoUmIoU: 18.31 -> 10.97Hurt
use description-length merge instead of fixed KMeans + pair merge (ablation)cluster construction · ScanRefer 3D mIoUmIoU: 21.23 -> 23.33Improved
add xyz cost to the description-length merge (ablation)scene-adaptive clustering · ScanRefer 3D mIoUmIoU: 23.33 -> 21.63Hurt
select Top-5 cluster union instead of Top-1 (ablation)scene-adaptive clustering · ScanRefer 3D mIoUmIoU: 23.33 -> 14.96Hurt
use multi-cluster Top-k union with fixed KMeans K=512 (ablation)fixed KMeans K=512 · ScanRefer 3D mIoUmIoU: 10.97 -> 14.62Improved
use frozen CLIP instead of frozen BERT as text encoder (ablation)ClusterSplat scorer · ScanRefer 3D mIoUmIoU: 14.62 -> 23.33Improved
use local VLM caption generators instead of GPT-4.1 (ablation)pseudo-caption source · ScanRefer 3D mIoUmIoU: 23.33 -> 21.23 (InternVL3.5-8B), 20.01 (Qwen3-VL-8B)Hurt
use cluster-level selection instead of primitive filtering on class-name queriesClusterSplat vs OpenGaussian · ScanNet v2 class name 3DmIoU: 31.05 -> 29.21 mIoU; mAcc 46.39 -> 46.60Mixed
use cluster-level selection on Ref-LERF versus ReferSplat with our lossClusterSplat · Ref-LERF averagemIoU: 26.59 -> 31.14Improved

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