Download presentation
Presentation is loading. Please wait.
1
Vision Reading Group, 2nd of May 2018 Martin Rünz
CodeSLAM — Learning a Compact, Optimisable Representation for Dense Visual SLAM Vision Reading Group, 2nd of May 2018 Martin Rünz
2
An alternative representation to depth maps is presented
In a nutshell An alternative representation to depth maps is presented
3
Background – Common Map Representations
Surfels Mesh Pose-Graph + Depth-Maps TSDF
4
Ideas Depth-maps are not random
5
Ideas Depth-maps are not random (especially in man-made environments)
6
Ideas Depth-maps are not random
A compact representation – code – can be learned by encoder Decoders are differentiable → code can be optimised (w.r.t. photometric loss...) This is useful in SfM or SLAM scenarios Reconstruct high-frequency details from color
7
Depth Reconstruction Depth-from-mono Depth-from-mono + code
Given this differentiable function, warping constraints can be used to optimise c and pose
8
Architecture Laplace distribution
Color feature extractor + uncertainty predictor Laplace distribution Only for training, ground-truth depth Decoder: CODE Variational autoencoder, to increase smoothness of mapping between code and depth Small changes in code → small changes in depth
9
Video
10
Inverse depth parametrization
average Error behaves more Gaussian original depth
11
Warping Both functions differentiable to inputs Transform → B 3D
Photometric error: Both functions differentiable to inputs Expensive (convolutions) Pre-computed if decoder is linear!
12
Application SfM Cost function:
Initialise poses and code with zero-vector Use residuals + Jacobians in Gauss-Newton style optimisation Cost function: Functionality of : Mask invalid correspondences Relative weighting Huber weighting Down-weight slanted surfaces Down-weight occluded pixels
13
Experiments SfM
14
Experiments SfM
15
Experiments SLAM
16
Experiments Setups
17
Experiments Setups
18
Experiments Influence code entries
19
Video
20
Thanks for listening!
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.