Nr-3D

The 'Nr-3D' dataset is used to evaluate zero-shot 3D visual grounding methods by providing a benchmark for locating target objects in 3D scenes based on natural language descriptions.

Papers using Nr-3D (5)

PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding2026Think While You Map: Asynchronous Vision-Language Agents for Incremental 3D Scene Graphs20263D CoCa v2: Contrastive Learners with Test-Time Search for Generalizable Spatial Intelligence2026Zero-shot 3D Visual Grounding From Vision-language Models2025TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding2021