LightSAL: Lightweight Sign Agnostic Learning for Implicit Surface Representation

TL;DR

LightSAL introduces a lightweight, efficient deep neural network for implicit 3D shape representation that maintains accuracy while reducing model size and training time, leveraging sign-agnostic learning with signed distance fields.

Contribution

The paper presents LightSAL, a novel convolutional architecture that improves efficiency in training and model size for implicit 3D shape learning, using sign-agnostic learning with signed distance fields.

Findings

Outperforms previous models in size and training speed

Achieves comparable accuracy to state-of-the-art methods

Demonstrates effectiveness on the D-Faust dataset

Abstract

Recently, several works have addressed modeling of 3D shapes using deep neural networks to learn implicit surface representations. Up to now, the majority of works have concentrated on reconstruction quality, paying little or no attention to model size or training time. This work proposes LightSAL, a novel deep convolutional architecture for learning 3D shapes; the proposed work concentrates on efficiency both in network training time and resulting model size. We build on the recent concept of Sign Agnostic Learning for training the proposed network, relying on signed distance fields, with unsigned distance as ground truth. In the experimental section of the paper, we demonstrate that the proposed architecture outperforms previous work in model size and number of required training iterations, while achieving equivalent accuracy. Experiments are based on the D-Faust dataset that contains 41k 3D scans of human shapes. The proposed model has been implemented in PyTorch.