AI Paper Atlas

Research map / 3D vision / 3D generation

REALM: An MLLM-Agent Framework for Open World 3D Reasoning Segmentation and Editing on Gaussian Splatting

Changyue Shi, Minghao Chen, Yiping Mao, Chuxiao Yang, Xinyuan Hu, Jiajun Ding, Zhou Yu

CVPR 2026 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 9 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 Qwen2.5-VL reasoning to GS-Group (ablation)GS-Group · LERF FigurinesmIoU: 0.32 -> 0.78Improved
add global reasoning (multi-view parallel MLLM voting) (ablation)REALM · LERF FigurinesmIoU: 0.78 -> 0.89Improved
add local refinement of the 3D mask (ablation)REALM · LERF FigurinesmIoU: 0.89 -> 0.95Improved
add K-means clustering of camera poses for global view selection (ablation)REALM · LERF FigurinesmIoU: 0.38 -> 0.95Improved
use Top-K-ID selection instead of random choice among K-means views (ablation)REALM · LERF FigurinesmIoU: 0.76 -> 0.95Improved
use K-means + Top-K-ID instead of totally random global views (ablation)REALM · LERF FigurinesmIoU: 0.59 -> 0.95Improved
vary number of K-means clusters (2, 24, 128) (ablation)REALM · LERF FigurinesmIoU: 0.76 (2) / 0.95 (24) / 0.56 (128)Mixed
increase number of global cameras from 4 to 8 (ablation)REALM · LERF FigurinesmIoU: 0.81 -> 0.95Improved
increase number of global cameras from 8 to 16 (ablation)REALM · LERF FigurinesmIoU: 0.95 -> 0.95No clear effect
increase local refinement steps from 50 to 500 or 1000 (ablation)REALM · LERF FigurinesmIoU: 0.95 -> 0.79 (500), 0.74 (1000)Hurt
reduce local refinement steps from 50 to 10 (ablation)REALM · LERF FigurinesmIoU: 0.95 -> 0.94No clear effect
replace MLLM aggregation with random views fed directly to the MLLM (ablation)REALM · LERF FigurinesmIoUHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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