Cap3D
Pillar scores are computed during the next indexing cycle.
- **Paper:** Scalable 3D Captioning with Pretrained Models - **Paper:** View Selection for 3D Captioning via Diffusion Ranking - **Repository**: Github_Cap3D - **Repository**: Github_DiffuRank - **Project**: Project This repository hosts data for Scalable 3D Captioning with Pretrained Models and View Selection for 3D Captioning via Diffusion Ranking, including descriptive **captions** for 3D objects in Objaverse...
| Entity Passport | |
| Registry ID | hf-dataset--tiange--cap3d |
| Provider | huggingface |
Cite this dataset
Academic & Research Attribution
@misc{hf_dataset__tiange__cap3d,
author = {tiange},
title = {Cap3D Dataset},
year = {2026},
howpublished = {\url{https://huggingface.co/datasets/tiange/Cap3D}},
note = {Accessed via Free2AITools Knowledge Fortress}
}π¬Technical Deep Dive
Full Specifications [+]βΎ
βοΈ Nexus Index V2.0
π¬ Index Insight
FNI V2.0 for Cap3D: Semantic (S:50), Authority (A:0), Popularity (P:0), Recency (R:0), Quality (Q:0).
Verification Authority
ποΈ Data Preview
Row-level preview not available for this dataset.
Schema structure is shown in the Field Logic panel when available.
π Explore Full Dataset β𧬠Field Logic
Schema not yet indexed for this dataset.
Dataset Specification
license: odc-by
viewer: false
task_categories:
- text-to-3d
- image-to-3d
Dataset Description
- Paper: Scalable 3D Captioning with Pretrained Models
- Paper: View Selection for 3D Captioning via Diffusion Ranking
- Repository: Github_Cap3D
- Repository: Github_DiffuRank
- Project: Project
This repository hosts data for Scalable 3D Captioning with Pretrained Models and View Selection for 3D Captioning via Diffusion Ranking, including descriptive captions for 3D objects in Objaverse, Objaverse-XL, ABO, and ShapeNet. This repo also includes point clouds and rendered images with camera, depth, and MatAlpha information of Objaverse objects, as well as their Shap-E latent codes. All the captions and data provided by our papers are released under ODC-By 1.0 license.
Important license & data remove information!
Please ensure compliance with the licenses specified for each object in the Objaverse annotations. Note that certain objects are not approved for commercial use.
If you are the creator of an asset and would like your 3D modelβs information removed from the Cap3D-DiffuRank dataset, please contact Tiange for assistance. We sincerely thank all contributorsβyour efforts are instrumental in advancing the 3D vision community. This dataset repository is a humble addition, built upon the foundation of your contributions and shared work.
Usage
| Filename | Description |
|---|---|
| Cap3D_automated_Objaverse_full.csv | Our captions generated by Cap3D and DiffuRank for Objaverse(-XL), including 1,604,291 3D-caption pairs. - 785,150 for Objaverse; - the remainder for Objaverse-XL, primarily from the high-quality subset described in Section 4.1 (Alignment Finetuning) of the Objaverse-XL paper, retrieved via alignment_annotations = oxl.get_alignment_annotations(); - identifiers of length <=32 characters are Objaverse 1.0 UIDs ( import objaverse; uids = objaverse.load_uids()), while those with 64 characters are SHA256 hashes from Objaverse-XL. |
| Cap3D_automated_ABO.csv | Our captions generated by Cap3D and DiffuRank for the ABO dataset, including both general and compositional descriptions. |
| Cap3D_automated_ShapeNet.csv | Our captions generated by Cap3D and DiffuRank for the ShapeNet dataset. |
| PointCloud_pt_zips | Provided by Cap3D and DiffuRank, 1,552,357 PointClouds (16,384 colorful points) extracted from Objaverse objects. Saved as .pt file. Each .pt file stores a torch.Tensor of shape [16384, 6] where [:, :3] are XYZ (float32) and [:, 3:6] are RGB normalized from [0,255] to [-1,1] via rgb/127.5-1.0. Converted from the .ply files in PointCloud_zips. |
| PointCloud_zips | Provided by Cap3D and DiffuRank, 1,552,357 PointClouds (16,384 colorful points) extracted from Objaverse objects. Saved as .ply file. compressed_pcs_{00~09}.zip are for Objaverse objects and compressed_pcs_{>=10}.zip for Objaverse-XL objects. |
| PointCloud_zips_ABO | Provided by Cap3D and DiffuRank, 7,953 PointClouds (16,384 colorful points) extracted from ABO objects. Saved as .ply file. |
| PointCloud_zips_ShapeNet | Provided by Cap3D and DiffuRank, 52,472 PointClouds (16,384 colorful points) extracted from ShapeNet objects. Saved as .ply file. |
| RenderedImage_perobj_zips | Provided by DiffuRank, Rendered images for 1,552,357 Objaverse objects. Once unzip compressed_imgs_perobj_xx.zip will have multiple zip files which consists of 20 rendered images along with camera details (intrinsic & extrinsic), depth data, and masks (one example). Please specify the unzip path, such as unzip ed51a51909ee46c780db3a85e821feb2.zip -d ed51a51909ee46c780db3a85e821feb2. compressed_imgs_perobj_{000~052}.zip are for Objaverse objects and compressed_imgs_perobj_{>=053}.zip for Objaverse-XL objects. More information are in here. |
| RenderedImage_perobj_zips_ABO | Provided by DiffuRank, Rendered images for 7,953 ABO objects. Details similar to the above. |
| RenderedImage_perobj_zips_ShapeNet | Provided by DiffuRank, Rendered images for 52,472 ShapeNet objects. Details similar to the above. |
| misc | Including miscellaneous files such as human-authored captions, finetuned models, objaverse pointclouds stored as .pt, shapE latent codes, and etc. Please refer to this README |
# load our captions
import pandas as pd
captions = pd.read_csv('Cap3D_automated_Objaverse_full.csv', header=None)
captions:
0 1
0 ed51a51909ee46c780db3a85e821feb2 Matte green rifle with a long barrel, stock, a...
1 9110b606f6c547b2980fcb3c8c4b6a1c Rustic single-story building with a weathered ...
2 80d9caaa1fa04502af666135196456e1 a pair of purple and black swords with white h...
3 28d43a218cd8466a8c1f82b29b71e314 3D model of a cluttered outdoor scene with veg...
4 75582285fab442a2ba31733f9c8fae66 Floating terrain piece with grassy landscape a...
... ... ...
1002417 3623e74f34c1c3c523af6b2bb8ffcbe2d2dce897ef61b9... Abstract 3D composition with human figures and...
1002418 64e9f7b7a1fc4c4ec56ed8b5917dfd610930043ac5e15f... 3D object with a rough, irregular pink surface...
1002419 fcd089d6a237fee21dfd5f0d6d9b74b2fd1150cdc61c7f... Bright pink abstract 3D model of a building wi...
1002420 f812dc980050f2d5f4b37df2a8620372f810dd6456a5f2... Monochromatic gray 3D model of a stylized huma...
1002421 77c09500b4d8e4b881e1ce6929d56c23658b87173c0996... Modular futuristic spacecraft with red and ora...
if u want to obtain the caption for specific UID
caption = captions[captions[0] == '80d9caaa1fa04502af666135196456e1'][1].values[0]
Citation Information
Please cite Objaverse, ABO, and ShapeNet paper accordingly, if you use related data.
@inproceedings{deitke2023objaverse,
title={Objaverse: A universe of annotated 3d objects},
author={Deitke, Matt and Schwenk, Dustin and Salvador, Jordi and Weihs, Luca and Michel, Oscar and VanderBilt, Eli and Schmidt, Ludwig and Ehsani, Kiana and Kembhavi, Aniruddha and Farhadi, Ali},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={13142--13153},
year={2023}
}
@article{deitke2024objaverse,
title={Objaverse-xl: A universe of 10m+ 3d objects},
author={Deitke, Matt and Liu, Ruoshi and Wallingford, Matthew and Ngo, Huong and Michel, Oscar and Kusupati, Aditya and Fan, Alan and Laforte, Christian and Voleti, Vikram and Gadre, Samir Yitzhak and others},
journal={Advances in Neural Information Processing Systems},
volume={36},
year={2024}
}
@inproceedings{collins2022abo,
title={Abo: Dataset and benchmarks for real-world 3d object understanding},
author={Collins, Jasmine and Goel, Shubham and Deng, Kenan and Luthra, Achleshwar and Xu, Leon and Gundogdu, Erhan and Zhang, Xi and Vicente, Tomas F Yago and Dideriksen, Thomas and Arora, Himanshu and others},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={21126--21136},
year={2022}
}
@article{chang2015shapenet,
title={Shapenet: An information-rich 3d model repository},
author={Chang, Angel X and Funkhouser, Thomas and Guibas, Leonidas and Hanrahan, Pat and Huang, Qixing and Li, Zimo and Savarese, Silvio and Savva, Manolis and Song, Shuran and Su, Hao and others},
journal={arXiv preprint arXiv:1512.03012},
year={2015}
}
If you find our data or code useful, please consider citing:
@article{luo2023scalable,
title={Scalable 3d captioning with pretrained models},
author={Luo, Tiange and Rockwell, Chris and Lee, Honglak and Johnson, Justin},
journal={Advances in Neural Information Processing Systems},
volume={36},
pages={75307--75337},
year={2023}
}
@inproceedings{luo2024view,
title={View selection for 3d captioning via diffusion ranking},
author={Luo, Tiange and Johnson, Justin and Lee, Honglak},
booktitle={European Conference on Computer Vision},
pages={180--197},
year={2024},
organization={Springer}
}
Social Proof
AI Summary: Based on Hugging Face metadata. Not a recommendation.
π‘οΈ Dataset Transparency Report
Verified data manifest for traceability and transparency.
π Identity & Source
- id
- hf-dataset--tiange--cap3d
- source
- huggingface
- author
- tiange
- tags
- task_categories:text-to-3dtask_categories:image-to-3dlicense:odc-byarxiv:2306.07279arxiv:2404.07984arxiv:2212.08051arxiv:2307.05663arxiv:2110.06199arxiv:1512.03012region:us
βοΈ Technical Specs
- architecture
- null
- params billions
- null
- context length
- null
π Engagement & Metrics
- likes
- 125
- downloads
- 33,347
Free2AITools Constitutional Data Pipeline: Curated disclosure mode active. (V15.x Standard)