# US 12,223,614 B2 · Systems and methods for generative drawing and customization of three-dimensional (“3D”) objects in 3D space using gestures > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,223,614 B2 - Document ID: US12223614B2 - Status: Granted - Kind: B2 - Application number: 18/479,533 - Filed: 2023-10-02 - Published: 2024-09-19 - Granted: 2025-02-11 - Earliest claimed: 2023-03-14 - Assignees: Illuscio, Inc. - Applicants: Illuscio, Inc. - Inventors: Kyle Kinkade - Web page: https://patentgrep.com/patent/US12223614B2 ## CPC - G06T 19/20: Editing of three-dimensional [3D] images, e.g. changing shapes or colours, aligning objects or positioning parts - G06F 3/011: {Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00)} - G06F 3/013: {Eye tracking input arrangements (G06F3/015 takes precedence)} - G06F 3/017: {Gesture based interaction, e.g. based on a set of recognized hand gestures (interaction based on gestures traced on a digitiser G06F3/04883)} - G06F 3/0304: {Detection arrangements using opto-electronic means (constructional details of pointing devices not related to the detection arrangement using opto-electronic means G06F3/033; optical digitisers G06F3/042)} - G06T 2200/24: involving graphical user interfaces [GUIs] - G06T 2219/2004: Aligning objects, relative positioning of parts - G06T 2219/2016: Rotation, translation, scaling - G06T 2219/2021: Shape modification - G06T 2219/2024: Style variation - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Disclosed is a system and associated methods for the generative drawing and customization of three-dimensional (“3D”) objects in 3D space using hand gestures. The system adapts the hand gestures as intuitive controls for rapidly creating and customizing the 3D objects to have a desired artistic effect or a desired look. The system selects a 3D model of a particular object in response to a first user input, sets a position in a virtual space at which to generate the particular object in response to a mapped position of a first hand gesture tracked in a physical space, and generates a first state representation of the particular object at the position in the virtual space in response to a second hand gesture. The first state representation presents the particular object at one of different modeled stages of the particular object lifecycle. ## Claims ### Claim 1 A method comprising: selecting an icon from a plurality of icons displayed in a user interface in response to a first user input, wherein each icon of the plurality of icons is associated with a different object, and wherein selecting the icon comprises activating functionality for generating a particular object with one of a plurality of modeled states specific to the particular object; detecting a second user input that specifies a position in a three-dimensional (“3D”) space of the user interface at which to generate the particular object; transitioning between the plurality of modeled states that are specific to the particular object in response to detecting a third user input at a position that commences immediately after the second user input or at a position that corresponds to a generated part of the particular object in the 3D space, and wherein the third user input is a different gesture or action than the second user input; and presenting the particular object at a particular modeled state from the plurality of modeled states at the position in the user interface specified by the second user input in response to said transitioning between the plurality of modeled states and ending at the particular modeled state with the third user input. ### Claim 2 (depends on 1) The method of claim 1 further comprising: detecting a fourth user input that selects between different sets of customizations that are modeled for the particular object at the particular modeled state; adjusting the particular modeled state of the particular object with a first set of customizations that are selected based on the fourth user input; and presenting the particular object with the first set of customizations applied to the particular modeled state. ### Claim 3 (depends on 2) The method of claim 2, wherein the third user input comprises a vertical gesture, and wherein the fourth user input comprises a horizontal gesture or a rotational gesture. ### Claim 4 (depends on 2) The method of claim 2, wherein the different sets of customizations apply one or more different seasonal, temporal, health, or disrepair effects to the particular object at the particular modeled state. ### Claim 5 (depends on 1) The method of claim 1, wherein each modeled state of the plurality of modeled states represents the particular object with different visual elements. ### Claim 6 (depends on 5) The method of claim 5 further comprising: changing visual elements of the particular object in response to transitioning between the plurality of modeled states with the third user input. ### Claim 7 (depends on 1) The method of claim 1 further comprising: detecting a fourth user input that changes a size of the particular object; and presenting the particular object at the particular modeled state selected with the third user input, at the position specified by the second user input, and at the size specified with the fourth user input. ### Claim 8 (depends on 1) The method of claim 1 further comprising: changing 3D constructs that form a shape of the particular object in the user interface in response to transitioning between the plurality of modeled states for the particular object with the third user input. ### Claim 9 (depends on 1) The method of claim 1, wherein each modeled state of the plurality of modeled states is associated with a different 3D representation of the particular object; and wherein presenting the particular object at the particular modeled state comprises presenting a particular 3D representation that is associated with the particular modeled state and that is selected using the third user input. ### Claim 10 (depends on 1) The method of claim 1, wherein the second user input is a first directional or rotational hand movement; and wherein the third user input is a second directional or rotational hand movement that differs from the first directional or rotational hand movement. ### Claim 11 (depends on 1) The method of claim 1 further comprising: presenting the particular object with a first shape and form in response to the third user input corresponding to a movement of a particular gesture by a first amount and the movement mapping to a selection of a first modeled state of the plurality of modeled states; and changing the particular object from the first shape and form to a different second shape and form in response to the third user input continuing the movement of the particular gesture by a second amount and the movement by the second amount mapping to a selection of a second modeled state of the plurality of modeled states. ### Claim 12 (depends on 1) The method of claim 1, wherein the plurality of modeled states represent the particular object at different ages. ### Claim 13 (depends on 1) The method of claim 1, wherein the plurality of modeled states represent the particular object at different levels of disrepair. ### Claim 14 (depends on 1) The method of claim 1, wherein the plurality of modeled states represent the particular object at different states of health. ### Claim 15 (depends on 1) The method of claim 1 further comprising: detecting a change from the second user input to the third user input at the position in the user interface specified by the second user input, wherein detecting the change comprises detecting that the second user input ends at the position in the user interface and that the third user input starts at the position in the user input; and wherein transitioning between the plurality of modeled states comprises: cycling between the plurality of modeled states based on an amount of the change detected from the second user input to the third user input, wherein the amount of the change corresponds to a number of the plurality of modeled states to transition between. ### Claim 16 (depends on 1) The method of claim 1 further comprising: receiving a fourth user input that selects a specific part from a plurality of parts of the particular object at the particular modeled state; and changing the particular modeled state of the specific part by presenting the specific part with a second plurality of modeled states that are specific to the specific part without changing the particular modeled state for other parts of the plurality of parts in response to a fifth user input that is provided after receiving the fourth user input. ### Claim 17 (depends on 1) The method of claim 1 further comprising: creating a spline that commences at the position specified by the second user input and that ends at a different position in the user interface based on a continued invocation of the second user input after specifying the position in the 3D space at which to generate the particular object; and determining one or more of a size, shape, and form of the particular object with the particular modeled state based on the spline. ### Claim 18 A computing system comprising: one or more hardware processors configured to: select an icon from a plurality of icons displayed in a user interface in response to a first user input, wherein each icon of the plurality of icons is associated with a different object, and wherein selecting the icon comprises activating functionality for generating a particular object with one of a plurality of modeled states specific to the particular object; detect a second user input that specifies a position in a three-dimensional (“3D”) space of the user interface at which to generate the particular object; transition between the plurality of modeled states that are specific to the particular object in response to detecting a third user input at a position that commences immediately after the second user input or at a position that corresponds to a generated part of the particular object in the 3D space, and wherein the third user input is a different gesture or action than the second user input; and present the particular object at a particular modeled state from the plurality of modeled states at the position in the user interface specified by the second user input in response to said transitioning between the plurality of modeled states and ending at the particular modeled state with the third user input. ### Claim 19 (depends on 18) The computing system of claim 18, wherein the one or more hardware processors are further configured to: detect a fourth user input that selects between different sets of customizations that are modeled for the particular object at the particular modeled state; adjust the particular modeled state of the particular object with a first set of customizations that are selected based on the fourth user input; and present the particular object with the first set of customizations applied to the particular modeled state. ### Claim 20 A non-transitory computer-readable medium storing program instructions that, when executed by one or more hardware processors of a computing system, cause the computing system to perform operations comprising: selecting an icon from a plurality of icons displayed in a user interface in response to a first user input, wherein each icon of the plurality of icons is associated with a different object, and wherein selecting the icon comprises activating functionality for generating a particular object with one of a plurality of modeled states specific to the particular object; detecting a second user input that specifies a position in a three-dimensional (“3D”) space of the user interface at which to generate the particular object; transitioning between the plurality of modeled states that are specific to the particular object in response to detecting a third user input at a position that commences immediately after the second user input or at a position that corresponds to a generated part of the particular object in the 3D space, and wherein the third user input is a different gesture or action than the second user input; and presenting the particular object at a particular modeled state from the plurality of modeled states at the position in the user interface specified by the second user input in response to said transitioning between the plurality of modeled states and ending at the particular modeled state with the third user input.