3 results about "Joint reconstruction" patented technology

The application discloses a TOF-PET reconstruction method based on implicit neural representation, which has a significant technical advantage in the deep integration of physical modeling and data-driven methods. Unlike traditional deep learning methods that rely only on large-scale training data for end-to-end mapping, the method explicitly embeds the physical forward model of TOF-PET imaging in the INR framework. By introducing a strict data consistency term, the network output always satisfies the system projection constraint and TOF response characteristics. This effectively avoids problems such as excessive smoothing, artifact enhancement, and structural distortion under adverse imaging conditions such as low count and low dose. The method achieves high-precision, quantifiable, and physically interpretable reconstruction results, significantly improving the reliability of the reconstructed image in clinical quantitative analysis. Without changing the overall modeling idea, the method can be flexibly extended to dynamic PET imaging, activity-attenuation joint reconstruction, motion compensation reconstruction, and multi-modal fusion tasks such as PET-CT and PET-MRI, and can handle a variety of complex imaging problems.

This invention discloses a method for joint reconstruction of refractive surfaces and underwater scenes based on 3D Gaussian ray tracing, belonging to the field of computer vision and 3D reconstruction technology. By designing a hybrid water surface representation method, the water surface is represented as a neural height field; refraction calculations are performed to obtain the corresponding rays after refraction through the water surface; the underwater scene is modeled as a 3D Gaussian field for underwater scene rendering; a multi-view image supervision model is constructed, a 3D reconstruction loss function is designed, and end-to-end joint optimization is performed; thus, joint reconstruction of refractive surfaces and underwater scenes based on 3D Gaussian ray tracing is achieved. This invention achieves high-precision reconstruction while ensuring fast training speed and real-time new perspective rendering frame rate, solving the technical problems of high computational cost, multi-view geometric inconsistency, and inability to efficiently extract and separate water surface and underwater geometric structures in existing underwater scene 3D reconstruction methods.