Papers of the day   All papers

∇SLAM: Dense SLAM meets Automatic Differentiation

Comments

Oct 24 2019 Krishna Murthy

Excited to announce our new work! "gradSLAM: Dense SLAM meets automatic differentiation" We leverage the power of autodiff frameworks to make dense SLAM fully differentiable. Paper: https://arxiv.org/abs/1910.10672 Project page: http://montrealrobotics.ca/gradSLAM/ Video: https://www.youtube.com/watch?v=2ygtSJTmo08&t=1s https://t.co/vhCS1faDVt
7 replies, 268 likes


Oct 24 2019 Tomasz Malisiewicz

gradSLAM: Dense SLAM meets Automatic Differentiation. Cool way to unify backends on GPU! One step closer to deep visual slam. https://arxiv.org/abs/1910.10672 #robotics #computervision #deeplearning https://t.co/bFamkwcBXK
3 replies, 204 likes


Jan 22 2020 Krishna Murthy

gradSLAM is now an @icra2020 paper. More on this to come! Kudos to the anonymous reviewers for extremely detailed reviews. @duckietown_coo @mautkiungli @MILAMontreal @UMontrealDIRO @CMU_Robotics
4 replies, 104 likes


Oct 24 2019 Ankur Handa

Very interesting work from @krrish94 and @duckietown_coo on making the SLAM pipeline fully differentiable. ∇SLAM: Dense SLAM meets automatic differentiation
1 replies, 28 likes


Oct 24 2019 Dmytro Mishkin

Wow
1 replies, 12 likes


Oct 24 2019 Ganesh Iyer

Our work on making dense SLAM fully differentiable to enable dense mapping in learning-based frameworks is out! Check out "gradSLAM: Dense SLAM meets automatic differentiation"! Please note: No ∇ students were harmed in the making of this work :)
0 replies, 3 likes


Oct 24 2019 arXiv CS-CV

gradSLAM: Dense SLAM meets Automatic Differentiation http://arxiv.org/abs/1910.10672
0 replies, 1 likes


Content