Thank you for your excellent work! I noticed that the camera pose and depth generated by the model are generated within a relative space, rather than the real world. How can the predicted spatial point cloud be reconstructed to fit within the real world?
Looking forward to your reply.
Thank you for your excellent work! I noticed that the camera pose and depth generated by the model are generated within a relative space, rather than the real world. How can the predicted spatial point cloud be reconstructed to fit within the real world?
Looking forward to your reply.