Mixing-Denoising Generalizable Occupancy Networks - Archive ouverte HAL
Communication Dans Un Congrès Année : 2024

Mixing-Denoising Generalizable Occupancy Networks

Résumé

While current state-of-the-art generalizable implicit neural shape models [7], [54] rely on the inductive bias of convolutions, it is still not entirely clear how properties emerging from such biases are compatible with the task of 3D reconstruction from point cloud. We explore an alternative approach to generalizability in this context. We relax the intrinsic model bias (i.e. using MLPs to encode local features as opposed to convolutions) and constrain the hypothesis space instead with an auxiliary regularization related to the reconstruction task, i.e. denoising. The resulting model is the first only-MLP locally conditioned implicit shape reconstruction from point cloud network with fast feed forward inference. Point cloud borne features and denoising offsets are predicted from an exclusively MLP-made network in a single forward pass. A decoder predicts occupancy probabilities for queries anywhere in space by pooling nearby features from the point cloud order-invariantly, guided by denoised relative positional encoding. We outperform the state-of-the-art convolutional method [7] while using half the number of model parameters.

Dates et versions

hal-04615189 , version 1 (18-06-2024)

Identifiants

Citer

Amine Ouasfi, Adnane Boukhayma. Mixing-Denoising Generalizable Occupancy Networks. 2024 International Conference on 3D Vision (3DV), Mar 2024, Davos, Switzerland. ⟨10.1109/3dv62453.2024.00086⟩. ⟨hal-04615189⟩
21 Consultations
0 Téléchargements

Altmetric

Partager

More