# US 11,077,620 B2 · Depth reconstruction in additive fabrication > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,077,620 B2 - Document ID: US11077620B2 - Status: Granted - Kind: B2 - Application number: 16/737,142 - Filed: 2020-01-08 - Published: 2020-07-16 - Granted: 2021-08-03 - Earliest claimed: 2019-01-08 - Assignees: Inkbit, LLC - Applicants: Inkbit, LLC - Inventors: Desai Chen; Wojciech Matusik - Web page: https://patentgrep.com/patent/US11077620B2 ## CPC - B29C 64/393: for controlling or regulating additive manufacturing processes - B33Y 50/02: for controlling or regulating additive manufacturing processes - G01B 9/02091: Tomographic interferometers, e.g. based on optical coherence - G06N 3/02: Neural networks - G06T 7/521: from laser ranging, e.g. using interferometry; from the projection of structured light - G06T 2207/10028: Range image; Depth image; 3D point clouds - G06T 2207/10101: Optical tomography; Optical coherence tomography [OCT] - B29C: SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING (making preforms B29B11/00; making laminated products by combining previously unconnected layers which become one product whose layers will remain together B32B37/00 - B32B41/00) - B33Y: ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING - G01B: MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A method for determining estimated depth data for an object includes scanning the object to produce scan data corresponding to a surface region of the object using a first scanning process, configuring an artificial neural network with first configuration data corresponding to the first scanning process, and providing the scan data as an input to the configured artificial neural network to yield the estimated depth data as an output, the estimated depth data representing a location of a part of the object in the surface region. ## Claims ### Claim 1 A method for determining estimated depth data for an object comprising: scanning the object to produce scan data corresponding to a surface region of the object using a first scanning process; configuring an artificial neural network with first configuration data corresponding to the first scanning process; and providing the scan data as an input to the configured artificial neural network to yield the estimated depth data as an output, the estimated depth data representing a location of a part of the object in the surface region; and determining a surface geometry of the object based at least in part on the estimated depth data. ### Claim 2 (depends on 1) The method of claim 1 wherein the object comprises an object under 3D additive fabrication according to a first fabrication process. ### Claim 3 (depends on 2) The method of claim 2 wherein the first configuration data corresponds to the first scanning process as well as the first fabrication process. ### Claim 4 (depends on 3) The method of claim 3 wherein configuring an artificial neural network with first configuration data comprising selecting said first configuration data from a set of available configuration data each associated with a different scanning and/or fabrication process. ### Claim 5 (depends on 1) The method of claim 1 further comprising: determining expected depth data for the surface region of the object; and providing the expected depth data with the scan data to the configured artificial neural network. ### Claim 6 (depends on 5) The method of claim 5 wherein the expected depth data includes a range of expected depths. ### Claim 7 (depends on 1) The method of claim 1 wherein scanning the object comprises optically scanning the object at the location on the surface of the object. ### Claim 8 (depends on 7) The method of claim 7 wherein scanning the object comprises optically scanning the object over a plurality of locations on the surface region of the object. ### Claim 9 (depends on 7) The method of method of claim 7 wherein scanning the object comprises scanning the object using optical coherence tomography. ### Claim 10 (depends on 1) The method of claim 1 wherein scanning the object further comprises processing raw scan data according to one or more of (1) a linearization procedure, (2) a spectral analysis procedure, and (3) a phase correction procedure to produce the scan data. ### Claim 11 (depends on 1) The method of claim 1 further comprising transforming the scan data from a time domain representation to a frequency domain representation prior to providing the scan data as input to the artificial neural network. ### Claim 12 (depends on 1) The method of claim 1 wherein the configured artificial neural network further yields a confidence measure associated with the estimated depth data. ### Claim 13 (depends on 1) The method of claim 1 further comprising providing scan data for a spatial neighborhood associated with the surface region of the object as input to the configured artificial neural network. ### Claim 14 (depends on 13) The method of claim 13 wherein the spatial neighborhood includes a plurality of parts of the object in the surface region. ### Claim 15 A system for determining estimated depth data for an object comprising: a sensor for scanning the object to produce scan data corresponding to a surface region of the object using a first scanning process; an artificial neural network configured with first configuration data corresponding to the first scanning process, the artificial neural network configured to determine the estimated depth data representing a location of a part of the object in the surface region, the artificial neural network having, one or more inputs for receiving the scan data, and an output for providing an estimated depth data; and one or more processors configured to determine a surface geometry of the object based at least in part on the estimated depth data. ### Claim 16 A method for determining estimated depth data for an object comprising: scanning the object to produce scan data corresponding to a surface region of the object using a first scanning process; configuring a first artificial neural network with first configuration data corresponding to the first scanning process; configuring a second artificial neural network with second configuration data corresponding to the first scanning process; providing the scan data as an input to the configured first artificial neural network to yield volumetric data representing a location of a part of the object in the surface region; providing the volumetric data to the configured second neural network to yield the estimated depth data as an output, the estimated depth data representing the location of the part of the object in the surface region; and determining a surface geometry of the object based at least in part on the estimated depth data. ### Claim 17 (depends on 16) The method of claim 16 further comprising: determining expected depth data for the surface region of the object; and providing the expected depth data with the scan data to the configured second artificial neural network. ### Claim 18 (depends on 16) The method of claim 16 wherein the expected depth data includes a range of expected depths. ### Claim 19 A method comprising: successively depositing layers of material to form a partially fabricated object, thereby increasing a thickness of the partially fabricated object along a depth axis of the object; for each of at least some of the deposited layers, after depositing the layer, scanning the object to produce scan data including volumetric information along the depth axis of the object; providing the scan data as an input to an artificial neural network configured using configuration data determined in a prior scanning process to yield estimated depth data as an output, the estimated depth data representing a location on a surface layer of the object along the depth axis; and determining a surface geometry of the object based at least in part on the estimated depth data.