mako443/Text2Pos-CVPR2022
Code, dataset and models for our CVPR 2022 publication "Text2Pos"
This project helps mobile robots understand where to go based on everyday language. You provide a detailed 3D map of an environment (a point cloud) and a text description of a specific location within it, like "near the red car by the entrance." The project then identifies that exact spot on the 3D map. It's for roboticists and AI researchers working on advanced navigation and human-robot interaction.
No commits in the last 6 months.
Use this if you are developing mobile robots or autonomous vehicles that need to interpret natural language commands for specific pick-up or delivery points within a 3D environment.
Not ideal if you need a pre-built, ready-to-deploy navigation system for a commercial product without deep AI integration.
Stars
54
Forks
6
Language
Python
License
—
Category
Last pushed
Jun 17, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mako443/Text2Pos-CVPR2022"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
NVlabs/FasterViT
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with...
ViTAE-Transformer/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose...