3D / Point Cloud
Objaverse
800K+ annotated 3D models for training 3D and multimodal models.
100K–1M·CC-BY·Point Cloud (LAS/PLY)
3D / Point Cloud
Hypersim · §6 depth format (tarred per scene)
Hypersim · §6 depth format (tarred per scene)
3DVLM Hypersim — §6 depth format Hypersim (Apple, ICCV 2021) reconverted to the 3DVLM project’s unified §6 on-disk format. 457 scenes, ~77,400 frames, V-Ray ground truth. License: CC BY-SA 3.0, same as the source. If you use this, please cite Roberts et al. (Hypersim) and apply share-alike terms to any derivatives. Layout One uncompressed .tar per scene at the repo root: hypersim/ ai 001 001.tar ai 001 002.tar … ai 055 010.tar 457 tars, ~620 MB… See the full description on the dataset page:
Source: Hugging Face Hub (helioom/3dvlm-hypersim). Metadata imported from the dataset’s Hub tags.