I have few questions, would highly appreciate your response -
Will BundleSDF be able to properly built mesh representations of the object at every instance of the video?
Scene: Both camera (ego vehicle) and some other target vehicle are moving. Maximum distance of the target vehicle can be at most 50 metres. I gave the segmentation masks of the target vehicle along with rgb and depth as input - will BundleSDF be able to produce mesh of the object at each frame with correct pose and orientation 6D?
if you have RGBD and instance masks for each of them, then it should be feasible
Again, if you have depth and masks, it should be feasible. But since this is a driving scene, there are some params that need to be adapted such as farthest depth clipping.
哥儿 @wing-kit @wenbowen123, Awesome work indeed!
I have few questions, would highly appreciate your response -
Will BundleSDF be able to properly built mesh representations of the object at every instance of the video?
Scene: Both camera (ego vehicle) and some other target vehicle are moving. Maximum distance of the target vehicle can be at most 50 metres. I gave the segmentation masks of the target vehicle along with rgb and depth as input - will BundleSDF be able to produce mesh of the object at each frame with correct pose and orientation 6D?