yd-yin / rotationlaplace Goto Github PK
View Code? Open in Web Editor NEW[ICLR 2023] A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation
[ICLR 2023] A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation
Hi! Your work is interesting. I previously adopt David's work which implemented the Matrix Fisher distribution (MF) for regressing rotations. And recently I tried switching to your proposed Rotation Laplace distribution (RL).
But I found that computing the negative log-likelihood of RL is not as efficient as MF, in both time and memory. I suspect it results from the size of the grid that you set to compute. The shape of the grid is (36864, 3, 3)
. So it inevitably slows down the computation of NLL_loss
.
It would make RL more applicable if the computation is optimized.
Hi, thanks for your excellent work. Rencently, I'm using the Rotation Laplace to do 3D pose estimation tasks. And I have tried some methods to transfer you released file grids3.npy
with 36864 3x3 rot_mats into a more sparse one (e.g., by calculating the geodesic distance between any mat and the unit mat [[1,0,0], [0,1,0], [0,0,1]]
and then downsampling). But how can I change it into a more dense one with more than 36864 mats? Hoping for your reply!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.