DeepDeform: Learning Non-Rigid RGB-D Reconstruction With Semi-Supervised Data

@article{Bozic2020DeepDeformLN,
  title={DeepDeform: Learning Non-Rigid RGB-D Reconstruction With Semi-Supervised Data},
  author={Aljaz Bozic and M. Zollh{\"o}fer and C. Theobalt and Matthias Nie{\ss}ner},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={7000-7010}
}
Applying data-driven approaches to non-rigid 3D reconstruction has been difficult, which we believe can be attributed to the lack of a large-scale training corpus. Unfortunately, this method fails for important cases such as highly non-rigid deformations. We first address this problem of lack of data by introducing a novel semi-supervised strategy to obtain dense inter-frame correspondences from a sparse set of annotations. This way, we obtain a large dataset of 400 scenes, over 390,000 RGB-D… Expand
4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface
Learning to Optimize Non-Rigid Tracking
Neural Non-Rigid Tracking
Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes
...
1
2
...

References

SHOWING 1-10 OF 70 REFERENCES
Real-Time Geometry, Albedo, and Motion Reconstruction Using a Single RGB-D Camera
Realtime geometry
  • albedo, and motion reconstruction using a single rgb-d camera. ACM Transactions on Graphics (TOG), 36(3):32
  • 2017
DynamicFusion: Reconstruction and tracking of non-rigid scenes in real-time
Embedded deformation for shape manipulation
3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions
ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes
VolumeDeform: Real-Time Volumetric Non-rigid Reconstruction
Topology-Aware Non-Rigid Point Cloud Registration
3D-CODED: 3D Correspondences by Deep Deformation
DoubleFusion: Real-Time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor
...
1
2
3
4
5
...