Travis Driver

Results 43 comments of Travis Driver

The Theia verifier yields much more accurate relative pose estimates, both pre and post two-view BA. The final bundle adjustment results are better overall (regressions on the order of 0.1...

> waiting on results on other datasets, do you see any regressions on data association metrics? I wonder if that is causing the BA regressions? Since they are significant, we...

Not a huge increase in performance, but I think that's expected since our reprojection error thresholds are relatively large. Those can be tuned in another PR. Also running on the...

![newplot (24)](https://github.com/borglab/gtsfm/assets/25347892/00ae9814-392d-4590-a5df-f517abaf5401) [visual_comparison_dashboard.zip](https://github.com/borglab/gtsfm/files/12652107/visual_comparison_dashboard.zip)

Is this still relevant?

I'm not sure I really agree with any of these changes. I think spreading the evaluation tasks around to all the different modules just increases complexity. I think more responsibility...

> Have you presented about this descriptor before? How useful is it? We found it to be the most effective feature for the AstroVision data: https://www.sciencedirect.com/science/article/pii/S0094576523000103

> could you post a link to the colab? The link is at the top of the notebook

> Can we put the following code chunk into a library function? > > ```shell > cameras, images, points3d = read_model("results/ba_output") > pcd = np.array([_p3d.xyz for _p3d in points3d.values()]) >...