Публикация

Предыдущая публикация

But estimating the true underlying surface, even locally, is extremely difficult. Decades of literature have been dedicated to designing point-based methods for (local) reconstruction. Often, even just estimating neighborhoods is really difficult. [26/35]

Nicole Feng

28 июл., 22:35

So instead of tweaking one particular surface-fitting model, we simply use fixed-size neighborhoods with a *data-driven* approach that can fit to an extremely large set of examples, with a far more sophisticated data-fitting model than we could craft purely by hand. [27/35]

Обсуждение

Ответы

Nicole Feng

28 июл., 22:35

We use a small transformer network that predicts the 6 polynomial coefficients encoding the local surface underlying a neighborhood. It trains in ~45 hours on one NVIDIA RTX 3090, and can then be applied to any point cloud without extra training. [28/35]

Ответ для Nicole Feng

Nicole Feng

28 июл., 22:35

We intentionally do *not* attempt end-to-end SDF learning. We rely on classical theory for convergence to true signed distance, and use the network only for the one component with no easy analytical solution (local surface fitting). [29/35]