RoMa: Revisiting Robust Lossses for Dense Feature Matching
Johan Edstedt, Qiyu Sun, Georg Bökman, Mårten Wadenbäck, Michael Felsberg
Arxiv 2023
NOTE!!! Very early code, there might be bugs
The codebase is in the roma folder.
In your python environment (tested on Linux python 3.10), run:
pip install -e .We provide two demos in the demos folder. Here's the gist of it:
from roma import roma_outdoor
roma_model = roma_outdoor(device=device)
# Match
warp, certainty = roma_model.match(imA_path, imB_path, device=device)
# Sample matches for estimation
matches, certainty = roma_model.sample(warp, certainty)
# Convert to pixel coordinates (RoMa produces matches in [-1,1]x[-1,1])
kptsA, kptsB = roma_model.to_pixel_coordinates(matches, H_A, W_A, H_B, W_B)
# Find a fundamental matrix (or anything else of interest)
F, mask = cv2.findFundamentalMat(
kptsA.cpu().numpy(), kptsB.cpu().numpy(), ransacReprojThreshold=0.2, method=cv2.USAC_MAGSAC, confidence=0.999999, maxIters=10000
)The experiments in the paper are provided in the experiments folder.
- First follow the instructions provided here: https://github.com/Parskatt/DKM for downloading and preprocessing datasets.
- Run the relevant experiment, e.g.,
torchrun --nproc_per_node=4 --nnodes=1 --rdzv_backend=c10d experiments/roma_outdoor.pypython experiments/roma_outdoor.py --only_test --benchmark mega-1500All our code except DINOv2 is MIT license. DINOv2 has an Apache 2 license DINOv2.
Our codebase builds on the code in DKM.
If you find our models useful, please consider citing our paper!
@article{edstedt2023roma,
title={{RoMa}: Revisiting Robust Lossses for Dense Feature Matching},
author={Edstedt, Johan and Sun, Qiyu and Bökman, Georg and Wadenbäck, Mårten and Felsberg, Michael},
journal={arXiv preprint arXiv:2305.15404},
year={2023}
}