🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!
-
Updated
Aug 27, 2024 - Python
🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!
[ECCV 2024 Best Paper Candidate & TPAMI 2025] PointLLM: Empowering Large Language Models to Understand Point Clouds
[ICCV 2025] Repo for Objaverse++, Curated 3D Object Dataset with Quality Annotations
A collection of advanced tools for large-scale high-quality mesh data preparing
A simple 3D asset retrieval system based on objaverse. Query any 3D asset using text(CN/EN) or images, inter-modal or cross-modal. Equipped with backend API service and front-end gradio demo.
[NeurIPS 2026] 3D-PLOT-LLM: Part-Level Object Tokens for 3D Large Language Models
Multi-view Objaverse dataset with 83K objects, 48 dome views each, RGB/normal/depth maps, captions, and an interactive 3D viewer.
A RAG that makes a 3D-asset library searchable in plain language. Each one is rendered, captioned by Florence-2, then embedded into a FAISS index.
DCC-MCP asset-provider skill for AI agents to sample Objaverse object IDs, inspect annotations, and download GLB models with guidance to retain object-level licenses and attribution.
To associate your repository with the objaverse topic, visit your repo's landing page and select "manage topics."