AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

OpenGround: Planning-based Online Perception for Open-World 3D Visual Grounding

Wenyuan Huang, zhenyu zhang, Zhao Wang, Zhou Wei, Ting Huang, Fang Zhao, Jian Yang

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 4 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 Task-Chain Planning order instead of Jump/Random/Difficulty/Relevance orders (ablation)OpenGround · OpenTargetAcc@0.50: 29.2 (Random) / 29.8 (Jump) / 31.5 (Difficulty) / 32.6 (Relevance) -> 34.2Improved
provide initial Mask3D OLT as prior (ablation)OpenGround · OpenTargetAcc@0.50: 27.1 -> 34.2Improved
use smaller VLM (Qwen3-VL-32B vs GLM-4.5V) (ablation)OpenGround · OpenTargetAcc@0.50: 34.2 -> 30.4Hurt
use context-guided view selection instead of SeeGround/SeqVLM/Struct2D views (ablation)OpenGround single-step grounding · OpenTargetAcc@0.50: 31.6 / 31.8 / 26.3 -> 34.2Improved
annotate previously grounded objects plus candidates instead of all candidates or all mentioned objects (ablation)OpenGround · OpenTargetAcc@0.50: 26.5 / 25.3 -> 34.2Improved
add structured query decomposition in VLM reasoning (ablation)OpenGround · OpenTargetAcc@0.50: 32.9 -> 34.2Improved
provide original non-annotated images to VLM (ablation)OpenGround · OpenTargetAcc@0.50: 33.6 -> 34.2Improved
maximize coverage of context objects in view selection (ablation)OpenGround · OpenTargetAccImproved
increase views V from 3 to 4 (ablation)OpenGround CGP · OpenTargetAcc: 0.52% gain, +33.3% viewsNo clear effect
use OpenGround with SPAZER backend (ablation)OpenGround · Nr3Daccuracy: 63.8 -> 64.8Improved
OpenGround vs SPAZER with GPT-4oOpenGround · Nr3Daccuracy: 63.8 -> 61.7Hurt
apply OpenGround to standard closed-set benchmarkOpenGround vs SeqVLM (Doubao) · ScanReferAcc@0.50: 49.6 -> 54.4Improved

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