Gabriele Berton

Hi, are there any news on this? By the way, I've added AnyLoc to [this VPR benchmarking repo](https://github.com/gmberton/VPR-methods-evaluation), if you find any problem with the AnyLoc in that repo feel...

Hi, you might find useful to know that I tried the [DINOv2-based SALAD](https://github.com/serizba/salad) and the speed is fine (only 4x slower than a ResNet50), so there might be some problem...

Hi, the challenge dataset does not have public labels and therefore we can't process it in the same way that we do with any other dataset, so we preferred not...

Usually we rely on the number of inliers (`num_inliers`) to estimate if two images match or not, which is also what we did in the paper. The only thing to...

Hey thank you for your quick reply! I tried to add it to my repo but I'm having two issues: 1) If I use it on a machine with only...

Hi, sorry for the late response. Did you try to test some VPR model on the dataset created by this code? Shouldn't the DISTANCE_BETWEEN_FRAMES be different between database and queries?

This is great, thank you @jarvisyjw !

Agree on all you both said. It would be good to add test, as the current ones can surely be improved. I also don't have experience with pytest so @isaaccorley...

Hi, we never tried on 360 images. I doubt any of these methods have been trained on 360 images, but the keypoints extraction should give acceptable results, and perhaps even...

@paidiakileswar if you want to have a look at existing benchmarks using all these models you can check [Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks](https://arxiv.org/abs/2408.16445) or [our...