Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries

Amine Ouasfi, Adnane Boukhayma
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38905-38918, 2024.

Abstract

Implicit Neural Representations have gained prominence as a powerful framework for capturing complex data modalities, encompassing a wide range from 3D shapes to images and audio. Within the realm of 3D shape representation, Neural Signed Distance Functions (SDF) have demonstrated remarkable potential in faithfully encoding intricate shape geometry. However, learning SDFs from sparse 3D point clouds in the absence of ground truth supervision remains a very challenging task. While recent methods rely on smoothness priors to regularize the learning, our method introduces a regularization term that leverages adversarial samples around the shape to improve the learned SDFs. Through extensive experiments and evaluations, we illustrate the efficacy of our proposed method, highlighting its capacity to improve SDF learning with respect to baselines and the state-of-the-art using synthetic and real data.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-ouasfi24a, title = {Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries}, author = {Ouasfi, Amine and Boukhayma, Adnane}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {38905--38918}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/ouasfi24a/ouasfi24a.pdf}, url = {https://proceedings.mlr.press/v235/ouasfi24a.html}, abstract = {Implicit Neural Representations have gained prominence as a powerful framework for capturing complex data modalities, encompassing a wide range from 3D shapes to images and audio. Within the realm of 3D shape representation, Neural Signed Distance Functions (SDF) have demonstrated remarkable potential in faithfully encoding intricate shape geometry. However, learning SDFs from sparse 3D point clouds in the absence of ground truth supervision remains a very challenging task. While recent methods rely on smoothness priors to regularize the learning, our method introduces a regularization term that leverages adversarial samples around the shape to improve the learned SDFs. Through extensive experiments and evaluations, we illustrate the efficacy of our proposed method, highlighting its capacity to improve SDF learning with respect to baselines and the state-of-the-art using synthetic and real data.} }
Endnote
%0 Conference Paper %T Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries %A Amine Ouasfi %A Adnane Boukhayma %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-ouasfi24a %I PMLR %P 38905--38918 %U https://proceedings.mlr.press/v235/ouasfi24a.html %V 235 %X Implicit Neural Representations have gained prominence as a powerful framework for capturing complex data modalities, encompassing a wide range from 3D shapes to images and audio. Within the realm of 3D shape representation, Neural Signed Distance Functions (SDF) have demonstrated remarkable potential in faithfully encoding intricate shape geometry. However, learning SDFs from sparse 3D point clouds in the absence of ground truth supervision remains a very challenging task. While recent methods rely on smoothness priors to regularize the learning, our method introduces a regularization term that leverages adversarial samples around the shape to improve the learned SDFs. Through extensive experiments and evaluations, we illustrate the efficacy of our proposed method, highlighting its capacity to improve SDF learning with respect to baselines and the state-of-the-art using synthetic and real data.
APA
Ouasfi, A. & Boukhayma, A.. (2024). Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:38905-38918 Available from https://proceedings.mlr.press/v235/ouasfi24a.html.

Related Material