UltraG-Ray: Physics-Based Gaussian Ray Casting for Novel Ultrasound View Synthesis

2026-03-30

AI Summary

Existing methods for synthesizing novel-view ultrasound images struggle to accurately model complex tissue structures and view-dependent acoustic effects, resulting in insufficient realism. This work proposes a learnable 3D Gaussian field representation for ultrasound scenes, explicitly encoding ultrasound-specific physical parameters—such as attenuation and reflectivity—into the Gaussian space for the first time. By integrating a physics-driven B-mode synthesis module with a novel Gaussian ray casting strategy, the method naturally captures view-dependent acoustic characteristics. Quantitative evaluations demonstrate significant improvements over state-of-the-art approaches, with up to a 15% gain in MS-SSIM, while qualitative results confirm enhanced anatomical fidelity and acoustic realism in the synthesized images.

Abstract

Novel view synthesis (NVS) in ultrasound has gained attention as a technique for generating anatomically plausible views beyond the acquired frames, offering new capabilities for training clinicians or data augmentation. However, current methods struggle with complex tissue and view-dependent acoustic effects. Physics-based NVS aims to address these limitations by including the ultrasound image formation process into the simulation. Recent approaches combine a learnable implicit scene representation with an ultrasound-specific rendering module, yet a substantial gap between simulation and reality remains. In this work, we introduce UltraG-Ray, a novel ultrasound scene representation based on a learnable 3D Gaussian field, coupled to an efficient physics-based module for B-mode synthesis. We explicitly encode ultrasound-specific parameters, such as attenuation and reflection, into a Gaussian-based spatial representation and realize image synthesis within a novel ray casting scheme. In contrast to previous methods, this approach naturally captures view-dependent attenuation effects, thereby enabling the generation of physically informed B-mode images with increased realism. We compare our method to state-of-the-art and observe consistent gains in image quality metrics (up to 15% increase on MS-SSIM), demonstrating clear improvement in terms of realism of the synthesized ultrasound images.

Problem

• novel view synthesis
• ultrasound imaging
• view-dependent effects
• acoustic simulation
• image realism

Innovation

• Gaussian ray casting
• physics-based rendering
• ultrasound novel view synthesis
• view-dependent attenuation
• 3D Gaussian field