BA
Thanks for this amazing work! The performance looks impressive. I was wondering if the BA implementation is included in this repository?
Hi we have not provided the implementation of BA in this repo, but you can check out VGGSfM for an early look
Do we need to compute point tracks to do BA? We need 2D-3D correspondences right? For Table 1 in your paper, is it just one global BA optimization for all cameras at once?
In your paper you say: "Note that our method directly predicts close-to-accurate point/depth maps, which can serve as a good initialization for BA. This eliminates the need for triangulation and iterative refinement in BA as done by [125], making our approach significantly faster (only around 2 seconds even with BA)"
Closing this issue as BA implementation has been uploaded.