AaltoVision/DGC-Net
A PyTorch implementation of "DGC-Net: Dense Geometric Correspondence Network"
This project helps computer vision researchers and practitioners accurately match individual pixels between two different images of the same scene, even when the viewpoints change significantly. You input two images, and it outputs a dense map showing how each pixel in the first image corresponds to a pixel in the second. This is ideal for anyone working on tasks requiring precise alignment or understanding of visual changes across images.
206 stars. No commits in the last 6 months.
Use this if you need to find precise pixel-level correspondences between two images, particularly when the camera angle or perspective has shifted.
Not ideal if you're looking for an off-the-shelf application for commercial use, as its license is for non-commercial purposes only and it requires a developer to integrate.
Stars
206
Forks
18
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 12, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AaltoVision/DGC-Net"
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.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
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...