Some mask confusion

[djdll]

hello,

1. I would like to ask why we got the mask in the network training, but we did not use the mask in the test code and got the scene without occlusion

2. You just input a 2D image to get the mask, can we use it in other image inpainting fields? We want to pay attention to the loss calculation on the environment instead of moving objects, but the output image has occluded objects, does this make it impossible to train the mask?

Thanks.

[rover-xingyu]

Hi, we use masks to mask out occlusions for reconstructing the static landscapes, and during testing, we just render the landscapes for novel view synthesis.

Using the occlusion handling insights of Ha-NeRF for image inpainting is interesting, but we have not tried it yet.