Objaverse-XL

Objaverse-XL is an open dataset of over 10 million 3D objects! With it, we train Zero123-XL, a foundation model for 3D, observing incredible 3D generalization abilities: 🧵👇

  Scale Comparison

Objaverse 1.0 was released back in December. It was a step in the right direction, but still relatively small with 800K objects. Objaverse-XL is over an order of magnitude larger and much more diverse!

  Unlocking Generalization

Compared to the… See the full description on the dataset page: https://huggingface.co/datasets/allenai/objaverse-xl.

Objaverse is a large dataset of objects with 800K+ (and growing) 3D models with descriptive captions, tags, and animations. Objaverse improves upon present day 3D repositories in terms of scale, number of categories, and in the visual diversity of instances within a category.

BS-Objaverse 660K Dataset Card

  Dataset details

Dataset type: BS-Objaverse 660k Dataset is a set of GPT4-Vision-powered multi-modal captions data. It is constructed to enhance modality alignment and fine-grained visual concept perception for describing detailed information about the shape, texture of Objaverse 3D object.

obj_descript_gpt_10k.json is generated by GPT4-Vision. objaverse660k_mvllava7b.json is generated by our MV-LLaVA trained on GPT4-Vision-generated data.… See the full description on the dataset page: https://huggingface.co/datasets/Zery/BS-Objaverse.

cheryyunl/objaverse dataset hosted on Hugging Face and contributed by the HF Datasets community

Objaverse-Rand6View

Github | Project Page | Paper

  1. Dataset Introduction

TL;DR: This dataset contains multi-view images that are rendered from a high-quality subset of Objaverse, used in MV-Adapter. Features:

Orthographic or perspective views (random) 1024x1024 resolution RGB, Depth, Normal, Camera

  2. Data Extraction

sudo apt-get install git-lfs git lfs install git clone https://huggingface.co/datasets/huanngzh/Objaverse-Rand6View cat… See the full description on the dataset page: https://huggingface.co/datasets/huanngzh/Objaverse-Rand6View.

NCJ/processed-objaverse dataset hosted on Hugging Face and contributed by the HF Datasets community

Objaverse++: Curated 3D Object Dataset with Quality Annotations

Paper


Code

Chendi Lin, Heshan Liu, Qunshu Lin, Zachary Bright, Shitao Tang, Yihui He, Minghao Liu, Ling Zhu, Cindy Le Objaverse++ is a dataset that labels 3D modeling objects in terms of quality score and other important traits for machine learning researchers. We meticulously curated a collection of Objaverse objects and developed an effective classifier capable of scoring the entire Objaverse. Our… See the full description on the dataset page: https://huggingface.co/datasets/cindyxl/ObjaversePlusPlus.

Diffusion4D is a large-scale, high-quality dynamic 3D(4D) dataset sourced from the vast 3D data corpus of Objaverse-1.0 and Objaverse-XL. We apply a series of empirical rules to filter the dataset. You can find more details in our paper. In this part, we will release the selected 4D assets, including:

Selected high-quality 4D object ID. A render script using Blender, providing optional settings to render your personalized data. Rendered 4D images by our team to save your GPU time. With 8 GPUs and a total of 16 threads, it took 5.5 days to render the curated objaverse-1.0 dataset.

rishitdagli/objaverse-renders dataset hosted on Hugging Face and contributed by the HF Datasets community

LightProp Dataset for Neural LightRig (CVPR 2025)

  Overview

This repo contains rendering dataset for our paper Neural LightRig. More information is on our project page Neural LightRig. metadata.json contains information on object uids used for training / validation / testing.

  Download

Clone the whole repo or download with snapshot_download. Merge the splits using zip -FF pbr_obj.zip merged.zip. Unzip with unzip merged.zip.

  License

The dataset are… See the full description on the dataset page: https://huggingface.co/datasets/zxhezexin/NLR-LightProp-Objaverse-Renderings.

MeshFleet is a filtered and annotated dataset of High Quality vehicles derived from Objaverse XL. It contains the sha256 of the objects together with consitent object captions and vehicle parameters.

Source: Objaverse 1.0 / Sketchfab

First time working with combining 3D models on meshmixer; very loose recreation of a cuneiform archival bench in the Late Bronze Age using what free .obj files I could get my hands on.

Source: Objaverse 1.0 / Sketchfab

This is the dataset for Objaverse-Xray

Old service Tea cup and plate. made with maya and substance painter. texture set is 4K and there is low and high poly models. PNG and EXR texture set. Source: Objaverse 1.0 / Sketchfab

Lamoka Point collected in Huntington County, Indiana. Catalog #: 12-Hu-750 Uploaded by: Carson Wright Christine Thompson, Carson Wright, and Kevin C. Nolan, 2021. ROI010-315-01, 3D Model .ply file. Recovered as part of Report of Investigations 10, An Archaeological Assessment of Huntington Reservoir: Identification, Prediction, Impact, William Wepler and Donald Cochran Source: Objaverse 1.0 / Sketchfab

Gobjaverse-LVIS: Dataset Card for Tailor3D

This dataset card is for the Tailor3D project. You can see the more information below.

Github Code: Link to Github Arxiv Paper: Link to Arxiv Project Page: Link to Project Youtube Video: Link to Youtube Hugging Face Demo: Link to Hugging Face Demo

  🏗️ Gobjaverse-LVIS

Objaverse contains 660K 3D objects with nearly 100 random rendering views. While Gobjaverse, a high-quality rendering of 280K objects from Objaverse. Each object… See the full description on the dataset page: https://huggingface.co/datasets/alexzyqi/Tailor3D-Gobjaverse-LVIS.

Source: Objaverse 1.0 / Sketchfab

Contains rendered views and captions from Objaverse XL objects. the objects are from the alignment and TRELLIS500K (over 1 Millionen processed objects) dataset. We downloaded and rendered 4 views of each object. We added TRELLIS and CAP3D Captions where available. If there were no captions we generated new captions with the large version of Florence 2. This is the base dataset we used to generate MeshFleet which is described in MeshFleet: Filtered and Annotated 3D Vehicle Dataset for Domain… See the full description on the dataset page: https://huggingface.co/datasets/DamianBoborzi/objaverse_processed_renders_and_captions.

Source: Objaverse 1.0 / Sketchfab