Three-dimensional structure estimation device, three-dimensional structure estimation method, program, and recording medium
The device uses perspective images to train a learning model for accurate three-dimensional structure estimation by correcting attenuation coefficients based on signed distances, addressing the limitations of existing methods like NeRF.
WO2026028619A1 Publication Date: 2026-02-05AIR WATER INC +1
6 Cites 0 Cited by
Patent Information
- Application Number
- PCT/JP2025/021242
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-07-31
- Filing Date
- 2025-06-12
- Publication Date
- 2026-02-05
AI Technical Summary
Technical Problem
Existing methods for estimating three-dimensional structures, such as NeRF, require a large number of captured images and struggle with accuracy, especially in the boundary portions, and fail to recognize depth information in perspective images.
Method used
A three-dimensional structure estimation device that uses multiple perspective images to train a learning model to output signed distances and attenuation coefficients, correcting these coefficients based on signed distances to accurately estimate the object's structure.
Benefits of technology
Enables accurate estimation of the object's three-dimensional structure, including internal details, without requiring a large number of images, and improves accuracy at object boundaries.
✦ Generated by Eureka AI based on patent content.
Abstract
The present invention enables more accurate estimation of a three-dimensional structure including an internal structure of a target without requiring a large number of captured images. A three-dimensional structure estimation device (10) includes: an acquisition unit (111) that acquires a plurality of fluoroscopic images obtained by imaging a target from mutually different directions; a learning unit (112) that, using the plurality of fluoroscopic images, learns a learning model to which input data indicating three-dimensional coordinates of an arbitrary point inside the target is input and which outputs first output data indicating a signed distance of the arbitrary point with respect to a surface of an internal structure possessed by the target and second output data indicating a first attenuation coefficient at the arbitrary point; a calculation unit (113) that inputs, to the learning model, input data indicating respective points inside the target and, by correcting the first attenuation coefficient indicated by the second output data on the basis of the signed distance indicated by the first output data, calculates second attenuation coefficients at the respective points inside the target; and an estimation unit (114) that estimates a three-dimensional structure of the target on the basis of the second attenuation coefficients at the respective points inside the target.
Need to check novelty before this filing date? Find Prior Art