SunghwanHong/Cost-Aggregation-transformers
Official implementation of CATs
This project helps computer vision researchers and engineers accurately find corresponding points between two different images, even if objects are distorted or viewed from new angles. You input two images, and it outputs a precise mapping of points showing how parts of the objects relate to each other. This is ideal for anyone working with visual data that requires understanding relationships between varying image perspectives or forms.
134 stars. No commits in the last 6 months.
Use this if you need to establish highly accurate semantic correspondence between objects in different images, especially when those objects might vary significantly in appearance or pose.
Not ideal if you are looking for a simple object detection or classification tool, as this focuses specifically on detailed pixel-level correspondence.
Stars
134
Forks
11
Language
Python
License
GPL-3.0
Category
Last pushed
Jan 10, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/SunghwanHong/Cost-Aggregation-transformers"
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...