MPI Sintel
Introduced by Daniel J. Butler et al. in A Naturalistic Open Source Movie for Optical Flow Evaluation
MPI (Max Planck Institute) Sintel is a dataset for optical flow evaluation that has 1064 synthesized stereo images and ground truth data for disparity. Sintel is derived from open-source 3D animated short film Sintel. The dataset has 23 different scenes. The stereo images are RGB while the disparity is grayscale. Both have resolution of 1024×436 pixels and 8-bit per channel.
Source: Fast Disparity Estimation using Dense Networks*Benchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
Sintel-clean
|
GMFlow
|
|||
|
Sintel-final
|
FlowFormer
|
|||
|
Sintel Clean unsupervised
|
MDFlow
|
|||
|
Sintel Final unsupervised
|
UpFlow
|
|||
|
MPI Sintel
|
DeCOMPnet
|
|||
|
MPI Sintel
|
MCnet [villegas2017mcnet]
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
