Research map / Vision-language and multimodal / Human and embodied modeling
AmbiRefer3D: 3D Visual Grounding with Referential Ambiguity
Rongjiang Zhu, Wei Kang, Zeqi Liu, Chen junyu, Shuo Yang, Xinxiao Wu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add interactive disambiguation on top of D-LISA | D-LISA · AmbiRefer3D real scenes (Mixture) | Accuracy: 9.81 -> 41.57 | Improved |
| add interactive disambiguation on top of M3DRef-CLIP | M3DRef-CLIP · AmbiRefer3D real scenes (Attribute + Spatial Relation) | Accuracy: 33.24 -> 37.21 | Improved |
| add Lstop (stopping loss) (ablation) | interactive framework (D-LISA) · AmbiRefer3D Mixture | Accuracy: accuracy 42.36 -> 41.57, AvgR 3.74 -> 3.39 | Mixed |
| add Lcand (candidate ranking loss) (ablation) | interactive framework (D-LISA) · AmbiRefer3D Mixture | Accuracy: 38.13 -> 41.57 | Improved |
| add Lsel (constraint selection loss) (ablation) | interactive framework (D-LISA) · AmbiRefer3D Mixture | Accuracy: 24.47 -> 41.57 | Improved |
| use highest-scoring candidate as vtarget instead of random (ablation) | interactive framework (D-LISA) · AmbiRefer3D Mixture | Accuracy: 28.92 -> 41.57 | Improved |
| use highest-scoring candidate as vtarget instead of mean aggregation (ablation) | interactive framework (D-LISA) · AmbiRefer3D Mixture | Accuracy: 21.09 -> 41.57 | Improved |
| learned adaptive constraint selector instead of random (ablation) | interactive framework (D-LISA) · AmbiRefer3D Mixture | Accuracy: 23.31 -> 41.57 | Improved |
| learned adaptive selector instead of heuristic greedy (ablation) | interactive framework (D-LISA) · AmbiRefer3D Mixture | Accuracy: 33.76 -> 41.57 | Improved |
| apply top-3 constraints at once instead of one per round (ablation) | interactive framework (D-LISA) · AmbiRefer3D Mixture | S@1 / Accuracy: S@1 26.07 -> 30.42; Acc 41.57 -> 37.88 | Mixed |
| increase maximum interaction rounds (ablation) | D-LISA + Ours · AmbiRefer3D | Accuracy | Improved |
Closest papers by meaning
- AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring (AAAI 2025 · similarity 0.90)
- CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding (ICLR 2024 · similarity 0.90)
- From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes (NeurIPS 2025 · similarity 0.90)
- MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations (NeurIPS 2024 · similarity 0.89)
- Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers (NeurIPS 2024 · similarity 0.89)
- DenseGrounding: Improving Dense Language-Vision Semantics for Ego-centric 3D Visual Grounding (ICLR 2025 · similarity 0.89)
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.
