TRAILab/GeneralObjectMapping
Official Code Repository for the CoRL 2024 Paper: "Toward General Object-Level Mapping from Sparse Views with 3D Diffusion Priors"
This tool helps robotics engineers or 3D designers accurately reconstruct the 3D shape and position of everyday objects (like a toy truck, chair, or apple) in a scene, even from just a few camera images. You input sparse camera views of an object, and it outputs a precise 3D model and its exact placement. This is ideal for those working on robotic perception or scene understanding.
No commits in the last 6 months.
Use this if you need to create detailed 3D maps of objects from limited visual data, without needing to train or fine-tune complex neural networks.
Not ideal if you're dealing with environments that require real-time mapping or if you lack basic technical expertise in setting up Python environments.
Stars
32
Forks
—
Language
Python
License
MIT
Category
Last pushed
Jan 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/TRAILab/GeneralObjectMapping"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
anchen1011/toflow
TOFlow: Video Enhancement with Task-Oriented Flow
NVlabs/nvdiffrec
Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and...
RuojinCai/doppelgangers
Doppelgangers: Learning to Disambiguate Images of Similar Structures
cvg/GlueStick
Joint Deep Matcher for Points and Lines 🖼️💥🖼️ (ICCV 2023)
microsoft/SpareNet
Style-based Point Generator with Adversarial Rendering for Point Cloud Completion (CVPR 2021)