Towards Generalising Neural Implicit Representations

by   Theo W. Costain, et al.

Neural implicit representations have shown substantial improvements in efficiently storing 3D data, when compared to conventional formats. However, the focus of existing work has mainly been on storage and subsequent reconstruction. In this work, we argue that training neural representations for both reconstruction tasks, alongside conventional tasks, can produce more general encodings that admit equal quality reconstructions to single task training, whilst providing improved results on conventional tasks when compared to single task encodings. Through multi-task experiments on reconstruction, classification, and segmentation our approach learns feature rich encodings that produce high quality results for each task. We also reformulate the segmentation task, creating a more representative challenge for implicit representation contexts.



page 1

page 2

page 3

page 4


MIME: Adapting a Single Neural Network for Multi-task Inference with Memory-efficient Dynamic Pruning

Recent years have seen a paradigm shift towards multi-task learning. Thi...

MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction

In recent years, neural implicit surface reconstruction methods have bec...

3D-PSRNet: Part Segmented 3D Point Cloud Reconstruction From a Single Image

We propose a mechanism to reconstruct part annotated 3D point clouds of ...

JIFF: Jointly-aligned Implicit Face Function for High Quality Single View Clothed Human Reconstruction

This paper addresses the problem of single view 3D human reconstruction....

X2Teeth: 3D Teeth Reconstruction from a Single Panoramic Radiograph

3D teeth reconstruction from X-ray is important for dental diagnosis and...

An Algorithm for the SE(3)-Transformation on Neural Implicit Maps for Remapping Functions

Implicit representations are widely used for object reconstruction due t...

PINs: Progressive Implicit Networks for Multi-Scale Neural Representations

Multi-layer perceptrons (MLP) have proven to be effective scene encoders...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.