OSCAR: Occupancy-based Shape Completion via Acoustic Neural Implicit Representations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wysocki, Magdalena, Buldu, Kadir Burak, Gafencu, Miruna-Alexandra, Azampour, Mohammad Farid, Navab, Nassir
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908873541025792
author Wysocki, Magdalena
Buldu, Kadir Burak
Gafencu, Miruna-Alexandra
Azampour, Mohammad Farid
Navab, Nassir
author_facet Wysocki, Magdalena
Buldu, Kadir Burak
Gafencu, Miruna-Alexandra
Azampour, Mohammad Farid
Navab, Nassir
contents Accurate 3D reconstruction of vertebral anatomy from ultrasound is important for guiding minimally invasive spine interventions, but it remains challenging due to acoustic shadowing and view-dependent signal variations. We propose an occupancy-based shape completion method that reconstructs complete 3D anatomical geometry from partial ultrasound observations. Crucially for intra-operative applications, our approach extracts the anatomical surface directly from the image, avoiding the need for anatomical labels during inference. This label-free completion relies on a coupled latent space representing both the image appearance and the underlying anatomical shape. By leveraging a Neural Implicit Representation (NIR) that jointly models both spatial occupancy and acoustic interactions, the method uses acoustic parameters to become implicitly aware of the unseen regions without explicit shadowing labels through tracking acoustic signal transmission. We show that this method outperforms state-of-the-art shape completion for B-mode ultrasound by 80% in HD95 score. We validate our approach both in-silico and on phantom US images with registered mesh models from CT labels, demonstrating accurate reconstruction of occluded anatomy and robust generalization across diverse imaging conditions. Code and data will be released on publication.
format Preprint
id arxiv_https___arxiv_org_abs_2603_08279
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle OSCAR: Occupancy-based Shape Completion via Acoustic Neural Implicit Representations
Wysocki, Magdalena
Buldu, Kadir Burak
Gafencu, Miruna-Alexandra
Azampour, Mohammad Farid
Navab, Nassir
Computer Vision and Pattern Recognition
Accurate 3D reconstruction of vertebral anatomy from ultrasound is important for guiding minimally invasive spine interventions, but it remains challenging due to acoustic shadowing and view-dependent signal variations. We propose an occupancy-based shape completion method that reconstructs complete 3D anatomical geometry from partial ultrasound observations. Crucially for intra-operative applications, our approach extracts the anatomical surface directly from the image, avoiding the need for anatomical labels during inference. This label-free completion relies on a coupled latent space representing both the image appearance and the underlying anatomical shape. By leveraging a Neural Implicit Representation (NIR) that jointly models both spatial occupancy and acoustic interactions, the method uses acoustic parameters to become implicitly aware of the unseen regions without explicit shadowing labels through tracking acoustic signal transmission. We show that this method outperforms state-of-the-art shape completion for B-mode ultrasound by 80% in HD95 score. We validate our approach both in-silico and on phantom US images with registered mesh models from CT labels, demonstrating accurate reconstruction of occluded anatomy and robust generalization across diverse imaging conditions. Code and data will be released on publication.
title OSCAR: Occupancy-based Shape Completion via Acoustic Neural Implicit Representations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.08279