This table lists the benchmark results for the 2D Optical Flow scenario.
| Method | Info | Accuracy (<20px) | EPE (pixel) |
|---|---|---|---|
 |  | ||
| PWC-Net |  | 0.748 | 22.674 |
| Deqing Sun, Xiaodong Yang, Ming-Yu Liu, Jan Kautz: PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume. CVPR 2018 | |||
| FlowNet 2.0 | | 0.685 | 27.610 |
| Eddy Ilg, Nikolaus Mayer, Tonmoy Saikia, Margret Keuper, Alexey Dosovitskiy, Thomas Brox: FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks. CVPR 2017 | |||
This table lists the benchmark results for the Non-rigid Reconstruction scenario.
| Method | Info | Geometry error (cm) | Deformation error (cm) |
|---|---|---|---|
| | ||
| OcclusionFusion | 0.386 | 2.800 | |
| Wenbin Lin, Chengwei Zheng, Jun-Hai Yong, Feng Xu: OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D Reconstruction. CVPR 2022 | |||
| Neural Non-rigid Tracking | 0.403 | 2.872 | |
| DeepDeform | 0.416 | 3.152 | |
| Aljaž Božič, Michael Zollhöfer, Christian Theobalt, Matthias Nießner: DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Data. CVPR 2020 | |||
| DynamicFusion | 1.078 | 6.179 | |
| Richard Newcombe, Dieter Fox, Steve Seitz: DynamicFusion: Reconstruction and Tracking of Non-rigid Scenes in Real-Time. CVPR 2015 | |||
| VolumeDeform | 7.485 | 20.841 | |
| Matthias Innmann, Michael Zollhöfer, Matthias Nießner, Christian Theobalt, Marc Stamminger: VolumeDeform: Real-time Volumetric Non-rigid Reconstruction. ECCV 2016 | |||