IP Library Granted Patent US 12682560
Granted Patent B2
US 12682560 · App. 18/432,502 · Granted Jul 14, 2026

Three-dimensional shape generation apparatus, three-dimensional shape generation system, three-dimensional shape generation method, and non-transitory recording medium

Inventor: Kagehiro Nagao (Kanagawa, JP)
Assignee: Ricoh Company, Ltd.
G06T17/00G06T7/11G06T7/30G06T7/50G06T2207/10028G06T2210/04G06T2210/56
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12682560
App. No.
18/432,502
Granted
Jul 14, 2026
Kind
B2
Abstract

A three-dimensional shape generation apparatus includes circuitry to generate three-dimensional shape information indicating a three-dimensional shape corresponding to a three-dimensional point cloud, using model shape information indicating a three-dimensional model shape. The model shape information includes model shape information of a frame, and the circuitry generates three-dimensional shape information of a frame using the model shape information of the frame based on point cloud information indicating the three-dimensional point cloud.

Claims (66)

1 . A three-dimensional shape generation apparatus comprising

circuitry configured to generate three-dimensional shape information indicating a three-dimensional shape corresponding to a three-dimensional point cloud, using model shape information indicating a three-dimensional model shape,

wherein the model shape information includes model shape information of a frame, and

wherein the circuitry is configured to generate three-dimensional shape information of the frame using the model shape information of the frame based on point cloud information indicating the three-dimensional point cloud.

2 . The three-dimensional shape generation apparatus according to claim 1 ,

wherein the model shape information further includes model shape information of a transparent member, and

wherein, in a case that the frame is a frame of a transparent member, the circuitry is configured to:

generate three-dimensional shape information of the transparent member using the model shape information of the transparent member; and

add the three-dimensional shape information of the transparent member to a region surrounded by the frame.

3 . The three-dimensional shape generation apparatus according to claim 2 ,

wherein the circuitry is further configured to determine that the frame is the frame of the transparent member in a case that the three-dimensional shape information of the frame indicates the frame of the transparent member.

4 . The three-dimensional shape generation apparatus according to claim 2 ,

wherein the circuitry is further configured to determine that the frame is the frame of the transparent member in a case that a point cloud corresponding to the three-dimensional shape information of the frame indicates the frame of the transparent member.

5 . The three-dimensional shape generation apparatus according to claim 4 ,

wherein the circuitry is configured to:

perform segmentation for labeling a specific point cloud in the three-dimensional point cloud; and

determine that the frame is the frame of the transparent member in a case that a low-density region is present between a first point cloud labeled as a first frame and a second point cloud labeled as a second frame by the segmentation, the low-density region being a region in which the three-dimensional point cloud has a density equal to or smaller than a threshold value.

6 . The three-dimensional shape generation apparatus according to claim 5 ,

wherein the circuitry is configured to:

perform registration for converting a first three-dimensional point cloud acquired by measurement from a first side of the frame and a second three-dimensional point cloud acquired by measurement from a second side opposite the first side of the frame into one unified three-dimensional point cloud; and

perform the segmentation after the registration.

7 . The three-dimensional shape generation apparatus according to claim 2 ,

wherein the point cloud information includes information on signal intensities of the three-dimensional point cloud, and the circuitry is configured to determine that the frame is the frame of the transparent member based on a gap in the signal intensities.

8 . The three-dimensional shape generation apparatus according to claim 1 ,

wherein the circuitry is further configured to transmit the three-dimensional shape information of the frame to a communication terminal that communicates with the three-dimensional shape generation apparatus.

9 . The three-dimensional shape generation apparatus according to claim 1 ,

wherein the circuitry is further configured to display the three-dimensional shape information of the frame on a display.

10 . A three-dimensional shape generation system comprising:

the three-dimensional shape generation apparatus according to claim 1 ; and

a communication terminal,

wherein the circuitry of the three-dimensional shape generation apparatus is further configured to transmit the three-dimensional shape information of the frame to the communication terminal, and

wherein the communication terminal includes terminal circuitry configured to:

receive the three-dimensional shape information of the frame from the three-dimensional shape generation apparatus; and

display the three-dimensional shape information of the frame on a display.

11 . A method for generating a three-dimensional shape, the method comprising

generating three-dimensional shape information indicating a three-dimensional shape corresponding to a three-dimensional point cloud, using model shape information indicating a three-dimensional model shape,

wherein the model shape information includes model shape information of a frame, and

wherein the generating includes generating three-dimensional shape information of the frame using the model shape information of the frame based on point cloud information indicating the three-dimensional point cloud.

12 . The method for generating the three-dimensional shape according to claim 11 ,

wherein the model shape information further includes model shape information of a transparent member, and

wherein, in a case that the frame is a frame of a transparent member:

generating three-dimensional shape information of the transparent member using the model shape information of the transparent member; and

adding the three-dimensional shape information of the transparent member to a region surrounded by the frame.

13 . The method for generating the three-dimensional shape according to claim 12 , further including

determining that the frame is the frame of the transparent member in a case that the three-dimensional shape information of the frame indicates the frame of the transparent member.

14 . The method for generating the three-dimensional shape according to claim 12 , further including

determining that the frame is the frame of the transparent member in a case that a point cloud corresponding to the three-dimensional shape information of the frame indicates the frame of the transparent member.

15 . The method for generating the three-dimensional shape according to claim 14 , further including

performing segmentation for labeling a specific point cloud in the three-dimensional point cloud; and

determining that the frame is the frame of the transparent member in a case that a low-density region is present between a first point cloud labeled as a first frame and a second point cloud labeled as a second frame by the segmentation, the low-density region being a region in which the three-dimensional point cloud has a density equal to or smaller than a threshold value.

16 . A non-transitory recording medium storing a plurality of program codes which, when executed by one or more processors, causes the one or more processors to perform a method, the method comprising

generating three-dimensional shape information indicating a three-dimensional shape corresponding to a three-dimensional point cloud, using model shape information indicating a three-dimensional model shape,

wherein the model shape information includes model shape information of a frame, and

wherein the generating includes generating three-dimensional shape information of the frame using the model shape information of the frame based on point cloud information indicating the three-dimensional point cloud.

17 . The method according to claim 16 ,

wherein the model shape information further includes model shape information of a transparent member, and

wherein, in a case that the frame is a frame of a transparent member:

generating three-dimensional shape information of the transparent member using the model shape information of the transparent member; and

adding the three-dimensional shape information of the transparent member to a region surrounded by the frame.

18 . The method according to claim 17 , further including

determining that the frame is the frame of the transparent member in a case that the three-dimensional shape information of the frame indicates the frame of the transparent member.

19 . The method according to claim 17 , further including

determining that the frame is the frame of the transparent member in a case that a point cloud corresponding to the three-dimensional shape information of the frame indicates the frame of the transparent member.

20 . The method according to claim 19 , further including

performing segmentation for labeling a specific point cloud in the three-dimensional point cloud; and

determining that the frame is the frame of the transparent member in a case that a low-density region is present between a first point cloud labeled as a first frame and a second point cloud labeled as a second frame by the segmentation, the low-density region being a region in which the three-dimensional point cloud has a density equal to or smaller than a threshold value.