Datasets › ScanRefer Dataset

ScanRefer Dataset

Introduced by Dave Zhenyu Chen et al. in ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language archive 2025-07-28

Contains 51,583 descriptions of 11,046 objects from 800 ScanNet scenes. ScanRefer is the first large-scale effort to perform object localization via natural language expression directly in 3D.

Source: ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language

Homepage Benchmarks Papers JSON

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

		First row (archive order)	Paper	Code
3D dense captioning	ScanRefer Dataset	3D CoCa CIDEr 85.42	3D CoCa: Contrastive Learners are 3D Captioners	AIGeeksGroup/3DCoCa	12	Compare

Papers archive 2025-07-28

12 shown of 12 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 63. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

			Date	Samples run Syntology
3D CoCa: Contrastive Learners are 3D Captioners	1	1	13 Apr 2025	not harvested
See It All: Contextualized Late Aggregation for 3D Dense Captioning	0	1	14 Aug 2024	not harvested
Bi-directional Contextual Attention for 3D Dense Captioning	0	1	13 Aug 2024	not harvested
Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning	1	1	6 Sep 2023	not harvested
End-to-End 3D Dense Captioning with Vote2Cap-DETR	1	1	6 Jan 2023	ran 1 of 3 samples (2 unverified)
Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training	1	1	1 Jan 2023	not harvested
Contextual Modeling for 3D Dense Captioning on Point Clouds	0	1	8 Oct 2022	not harvested
Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds	1	1	22 Apr 2022	not harvested
MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes	1	1	10 Mar 2022	ran 2 of 9 samples (7 unverified)
X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning	1	1	2 Mar 2022	not harvested
3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds	0	1	1 Jan 2022	not harvested
Scan2Cap: Context-aware Dense Captioning in RGB-D Scans	0	1	3 Dec 2020	not harvested

Dataset loaders archive 2025-07-28

daveredrum/ScanReferpytorch

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Object Detection Object Localization Sentence Embeddings 3D dense captioning

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

ScanRefer Dataset

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections