OpenCodePapers
3d-dense-captioning-on-scanrefer-dataset
Image Captioning
3D Captioning
3D dense captioning
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Show papers without code
Paper
Code
CIDEr
↕
BLEU-4
↕
METEOR
↕
ROUGE-L
↕
ModelName
ReleaseDate
↕
3D CoCa: Contrastive Learners are 3D Captioners
✓ Link
85.42
45.56
30.95
61.98
3D CoCa
2025-04-13
See It All: Contextualized Late Aggregation for 3D Dense Captioning
83.14
42.17
27.92
59.44
See It All
2024-08-14
Bi-directional Contextual Attention for 3D Dense Captioning
80.14
40.16
27.76
56.10
BiCA
2024-08-13
PVCap: Towards Accurate 3D Dense Captioning via PseudoCap and VoxelCapNet
77.33
40.78
29.39
62.73
PVCap-Swin3D (MLE)
2026-07-07
Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning
✓ Link
76.36
41.37
28.70
60.00
Vote2Cap-DETR++
2023-09-06
PVCap: Towards Accurate 3D Dense Captioning via PseudoCap and VoxelCapNet
72.21
40.95
28.83
62.88
PVCap-SparseUNet (MLE)
2026-07-07
End-to-End 3D Dense Captioning with Vote2Cap-DETR
✓ Link
71.45
39.34
28.25
59.33
Vote2Cap-DETR
2023-01-06
3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds
60.86
39.67
27.45
59.02
3DJCG
2022-01-01
MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes
✓ Link
58.89
35.41
26.36
55.41
MORE
2022-03-10
Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds
✓ Link
58.06
35.30
26.16
55.03
SpaCap3d
2022-04-22
Scan2Cap: Context-aware Dense Captioning in RGB-D Scans
53.73
34.25
26.14
54.95
Scan2Cap
2020-12-03
Contextual Modeling for 3D Dense Captioning on Point Clouds
50.29
26.64
22.57
44.71
Contextual
2022-10-08
Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training
✓ Link
50.02
31.87
24.53
51.17
3D-VLP
2023-01-01
X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning
✓ Link
41.52
23.83
21.90
44.97
χ-Tran2Cap
2022-03-02
×