Distortion-Aware Convolutional Filters for Dense Prediction in Panoramic Images
Open paper
Benchmark
Model
Rank
Results
depth-estimation-on-stanford2d3d-panoramic
DisConv
–
RMSE: 0.369
absolute relative error: 0.176
semantic-segmentation-on-stanford2d3d-1
DisConv
–
mIoU: 34.6%
Rank counts only results with a code link.