Just Go With the Flow: Self-Supervised Scene Flow Estimation

@article{Mittal2020JustGW,
  title={Just Go With the Flow: Self-Supervised Scene Flow Estimation},
  author={Himangi Mittal and Brian Okorn and David Held},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={11174-11182}
}
When interacting with highly dynamic environments, scene flow allows autonomous systems to reason about the non-rigid motion of multiple independent objects. This is of particular interest in the field of autonomous driving, in which many cars, people, bicycles, and other objects need to be accurately tracked. Current state-of-the-art methods require annotated scene flow data from autonomous driving scenes to train scene flow networks with supervised learning. As an alternative, we present a… Expand
Self-Supervised Pillar Motion Learning for Autonomous Driving
Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motion in Dynamic 3D Scenes
Weakly Supervised Learning of Rigid 3D Scene Flow
Adversarial Self-Supervised Scene Flow Estimation
Do not trust the neighbors! Adversarial Metric Learning for Self-Supervised Scene Flow Estimation
Temporal LiDAR Frame Prediction for Autonomous Driving
Scene Flow from Point Clouds with or without Learning
Neural Ray Surfaces for Self-Supervised Learning of Depth and Ego-motion
Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walk
FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Clouds
...
1
2
3
...

References

SHOWING 1-10 OF 32 REFERENCES
Object scene flow for autonomous vehicles
Joint 3d Estimation of Vehicles and Scene Flow
Object scene flow
PointFlowNet: Learning Representations for Rigid Motion Estimation From Point Clouds
FlowNet3D: Learning Scene Flow in 3D Point Clouds
  • Xingyu Liu, C. Qi, L. Guibas
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
Learning Scene Flow in 3D Point Clouds
Learning Correspondence From the Cycle-Consistency of Time
Kinecting the dots: Particle based scene flow from depth sensors
  • S. Hadfield, R. Bowden
  • Mathematics, Computer Science
  • 2011 International Conference on Computer Vision
  • 2011
Are we ready for autonomous driving? The KITTI vision benchmark suite
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
  • N. Mayer, Eddy Ilg, +4 authors T. Brox
  • Computer Science, Mathematics
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
...
1
2
3
4
...