You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
You need to conduct a dataset similar to the OpenLane-V2 format to infer on the model.
Note that custom data input will result in very bad outputs. The model is not designed to be generalized to different camera settings and data sources.
thank you for your reply, do I need all 7 images? front_center, front_left etc.? Also how do I get camera's intrinsic K and distortion from google street view images?
Activity
sephyli commentedon May 5, 2025
You need to conduct a dataset similar to the OpenLane-V2 format to infer on the model.
Note that custom data input will result in very bad outputs. The model is not designed to be generalized to different camera settings and data sources.
jianyunli commentedon May 5, 2025
thank you for your reply, do I need all 7 images? front_center, front_left etc.? Also how do I get camera's intrinsic K and distortion from google street view images?