3 D Motion Decomposition for RGBD Future Dynamic Scene Synthesis

@inproceedings{Qi20193DM,
  title={3 D Motion Decomposition for RGBD Future Dynamic Scene Synthesis},
  author={Xiaojuan Qi and Zhengzhe Liu and Jingxi Jia and YouTu Lab},
  year={2019}
}
A future video is the 2D projection of a 3D scene with predicted camera and object motion. Accurate future video prediction inherently requires understanding of 3D motion and geometry of a scene. In this paper, we propose a RGBD scene forecasting model with 3D motion decomposition. We predict ego-motion and foreground motion that are combined to generate a future 3D dynamic scene, which is then projected into a 2D image plane to synthesize future motion, RGB images and depth maps. Optional… CONTINUE READING

Figures and Tables from this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 38 REFERENCES

Predicting Deeper into the Future of Semantic Segmentation

  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Dual Motion GAN for Future-Flow Embedded Video Prediction

  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

A benchmark for the evaluation of RGB-D SLAM systems

  • 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2012
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers