Closed mohcenaouadj closed 1 month ago
@HengyiWang thank you a lot for your answer
This is because the coordinate encoding is continuous. With the inherent smoothness of MLPs, once you start to train the model, it can have some sort of extrapolation (It naturally fits indoor scene reconstruction as most parts of the scene are flat (floor, wall, etc).
Thanks a lot
Hi @mohcenaouadj,
That is a great question. In fact, since you already know that you only have one object around the center, you can do a good initialization of the SDF field. In our new paper MorpheuS, we initialize the SDF into an approximate sphere using something similar to https://arxiv.org/abs/2002.10099. I think you can try this implicit initialization or just use a fixed blob function and let the model fit the SDF residual.