Dmytro Mishkin
@ducha-aiki.bsky.social
Marrying classical CV and Deep Learning. I do things, which work, rather than being novel, but not working.
http://dmytro.ai
http://dmytro.ai
Reposted by Dmytro Mishkin
@ducha-aiki.bsky.social you may be interested in this, Viktor implemented covariance weighted RANSAC, should hopefully be in poselib main pretty soon (already available here: github.com/PoseLib/Pose...)
PoseLib/test_cov.py at two_view_covariance · PoseLib/PoseLib
Minimal solvers for calibrated camera pose estimation - PoseLib/PoseLib
github.com
November 20, 2025 at 9:28 AM
@ducha-aiki.bsky.social you may be interested in this, Viktor implemented covariance weighted RANSAC, should hopefully be in poselib main pretty soon (already available here: github.com/PoseLib/Pose...)
Will you share this version of RANSAC? Or is it already in PoseLib? :)
November 20, 2025 at 9:27 AM
Will you share this version of RANSAC? Or is it already in PoseLib? :)
SatAst benchmark, I love it
November 20, 2025 at 9:21 AM
SatAst benchmark, I love it
RoMa v2 results.
November 20, 2025 at 9:08 AM
RoMa v2 results.
DA3
Architecture and prediction target ablations
3/3
Architecture and prediction target ablations
3/3
November 17, 2025 at 4:45 PM
DA3
Architecture and prediction target ablations
3/3
Architecture and prediction target ablations
3/3
DA3 2/3
Synthetic teacher == DAv2-like model to process real world datasets like MegaDepth, and get them dense and sharp depth.
Also great section of dataset issues in Appendix
Synthetic teacher == DAv2-like model to process real world datasets like MegaDepth, and get them dense and sharp depth.
Also great section of dataset issues in Appendix
November 17, 2025 at 4:45 PM
DA3 2/3
Synthetic teacher == DAv2-like model to process real world datasets like MegaDepth, and get them dense and sharp depth.
Also great section of dataset issues in Appendix
Synthetic teacher == DAv2-like model to process real world datasets like MegaDepth, and get them dense and sharp depth.
Also great section of dataset issues in Appendix
OMG, what is going on there?
November 14, 2025 at 7:41 PM
OMG, what is going on there?
Have you given the same advice for the MegaDepth paper?)
200k images, 196 locations, nothing is 1M or more
200k images, 196 locations, nothing is 1M or more
November 13, 2025 at 8:09 PM
Have you given the same advice for the MegaDepth paper?)
200k images, 196 locations, nothing is 1M or more
200k images, 196 locations, nothing is 1M or more
Just run person detection and blur the hands ;)
November 13, 2025 at 10:57 AM
Just run person detection and blur the hands ;)