OpenCodePapers

3d-dense-captioning-on-nr3d

Image Captioning3D dense captioning
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeCIDErBLEU-4METEORROUGE-LModelNameReleaseDate
3D CoCa: Contrastive Learners are 3D Captioners✓ Link52.8429.2925.5556.433D CoCa2025-04-13
Bi-directional Contextual Attention for 3D Dense Captioning48.7728.3525.6055.81BiCA2024-08-13
Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning✓ Link47.0827.7025.4455.22Vote2Cap-DETR++2023-09-06
End-to-End 3D Dense Captioning with Vote2Cap-DETR✓ Link43.8426.6825.4154.43Vote2Cap-DETR2023-01-06
3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds38.0622.8223.7752.993DJCG2022-01-01
Contextual Modeling for 3D Dense Captioning on Point Clouds35.2620.4222.7750.78Contextual2022-10-08
Complete 3d relationships extraction modality alignment network for 3d dense captioning34.8120.3723.0150.99REMAN2024-08-01
D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding33.8520.7023.1353.38D3Net2021-12-02
Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds✓ Link33.7119.9222.6150.50SpaCap3d2022-04-22
Scan2Cap: Context-aware Dense Captioning in RGB-D Scans27.4717.2421.8049.06Scan2Cap2020-12-03
Check out how to contribute new results.