Thank you for your great work and sharing it! While studying your paper I was a little confused about how the 3D gaussians from different bins are created and optimized.
I am specifically confused about: "For the subsequent bins, we use the Gaussians from the previous bin as the position priors [...]". Could you please explain:
How are the previous gaussians used as position priors? I thought the LiDAR pointcloud was used as initialization
Do you also divide the whole LiDAR pointcloud into bins and use the separate pointcloud chunks to initialize new gaussians in every bin?
Another related doubt I had is regarding the optimization. As far as I can understand from Figure 3 (see below) and Figure 8, the whole map is being kept in GPU memory and optimized jointly even as new bins are added to the scene.
Could you please confirm whether that is the case?
Do you have any specific adjustments to the optimization strategy as the camera moves further and further from the initial bin?
1) The LiDAR point cloud is used as the initialization for Gaussians
2) Yeah, we divide the whole LiDAR point cloud into bins
3) During optimization, the latter bin is stitched to the former ones directly
Thank you for your great work and sharing it! While studying your paper I was a little confused about how the 3D gaussians from different bins are created and optimized.
I am specifically confused about: "For the subsequent bins, we use the Gaussians from the previous bin as the position priors [...]". Could you please explain:
Another related doubt I had is regarding the optimization. As far as I can understand from Figure 3 (see below) and Figure 8, the whole map is being kept in GPU memory and optimized jointly even as new bins are added to the scene.
Thank you in advance for your help!