LPM: 3D Lungs Reconstruction using Lungs Parametric Model

CVPR 2025 Workshop Robo-3Dvlm Submission9 Authors

Keywords: 3D Lungs Reconstruction, neural parametric models, implicit surface representation, DeepSDF, medical imaging

TL;DR: We propose to learn a neural parametric implicit 3D representation of human lungs using neural signed distance fields

Abstract: Deep learning techniques have been proven fruitful for many researchers in the computer vision field for problems like image segmentation and object recognition. With the success of this, 3D reconstruction has been of great interest, and how Deep Learning can be used to implement the same. There have been plenty of successfully developed models and methods that take Computer Tomography (CT) scans as an input, then pre-processed to obtain the specific organ (lungs, liver, heart, etc.) and offer a stacked 3D representation of the organ as output. This paper reviews some of the recent papers that offer a different approach on how a 3D object can be constructed from an X-ray image alone, along with the challenges that come with such. This paper will provide insights into the development of a model capable of reconstructing 3D lung structures from point cloud data, utilizing real-world datasets. Additionally, it will explore the application of latent code for generating a broader dataset of lung models. This approach has the potential to aid in identifying the size and shape of lungs directly from X-ray images.

Submission Number: 9