search

dongkwonjin / RVLD

Official code for "Recursive Video Lane Detection", ICCV 2023
Apache License 2.0
77 stars 9 forks source link

How to do inference on single image #14

Open RohitKeshari opened 9 months ago

RohitKeshari commented 9 months ago

I am curious to see the generalization of model on different dataset, and to do this, wanted to visualize the output of your model on unseen image.

dongkwonjin commented 8 months ago

When I did generalization tests between VIL-100 and OpenLane-V, the proposed algorithm underperformed. This is because the two datasets are different in terms of camera heights, scene context, and the maximum number of lanes. But, existing methods such as CLRNet and GANet also exhibited such issues.

Thank you for your attention!