AI Paper Atlas

Research map / 3D vision / Gaussian splatting

ZeroSplat: Generalized Referring Segmentation in 3D Gaussian Splatting

Jiayu Ding, Meilu Song, Xiaoyi Zhang, Hongbo Jin, Yichen Jin, Xiangtian Si

ECCV 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 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
add VLM spatial anchoring (ablation)ZeroSplat mask lifting · GR-ScanNet (generalized referring)mIoU: 24.7 -> 38.6Improved
add 3D KNN diffusion alone (ablation)ZeroSplat mask lifting · GR-ScanNet (generalized referring)mIoU: 24.7 -> 26.2Improved
add 3D KNN diffusion on top of VLM (ablation)ZeroSplat · GR-ScanNet (generalized referring)mIoU: 38.6 -> 41.2Improved
add semantic label extraction (ablation)ZeroSplat VLM module · GR-ScanNet (generalized referring)mIoU: 24.3 -> 41.2Improved
add bounding box filter (ablation)ZeroSplat VLM module · GR-ScanNet (generalized referring)mIoU: 40.1 -> 41.2Improved
use geometric keyframe selection instead of random sampling (ablation)ZeroSplat VLM module · GR-ScanNet (generalized referring)mIoU: 39.6 -> 41.2Improved
use 3D KNN diffusion instead of 3D radius search (ablation)ZeroSplat refinement · GR-ScanNet (generalized referring)mIoU: 39.8 -> 41.2Improved
add spatial refinement (3D radius search) (ablation)ZeroSplat · GR-ScanNet (generalized referring)mIoU: 38.6 -> 39.8Improved
use Qwen3-VL-30B-A3B instead of Qwen3-VL-8B (ablation)ZeroSplat · GR-LERFmIoU: 49.4 -> 50.8Improved
use closed-source Qwen3-VL-Plus instead of open 30B modelZeroSplat · GR-LERFmIoU: 50.8 -> 56.7Improved
lower tau_safe to 0 (disable safety mechanism) (ablation)ZeroSplat · GR-LERF waldo-kitchenmIoU: 48.4 -> 29.3Hurt
lower tau_conf from 0.8 to 0.4 (ablation)ZeroSplat · GR-LERF waldo-kitchenmIoU: 48.4 -> 51.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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