Optimizing image capture for training machine-learned models for implicit representation

A user computing device, comprising:

• one or more processor devices;
• and
• one or more tangible, non-transitory computer readable media storing computer-readable instructions that when executed by the one or more processor devices cause the one or more processor devices to perform operations, the operations comprising:
• obtaining, from a computing system, capture information comprising instructions to a user of the user computing device to capture a plurality of image sets for a Point of Interest (POI), and wherein the instructions indicate that a distance, between the user computing device and surfaces of the POI, from which to capture the plurality of image sets is greater than a threshold distance;
• responsive to obtaining the capture information, obtaining the plurality of image sets for the POI, wherein the plurality of image sets are captured by the user via an image capture device, and wherein the plurality of image sets comprises:
• a calibration image set comprising a plurality of calibration image pairs, each of the calibration image pairs comprising two calibration images captured at two different locations within the POI that are separated by a pre-defined distance;
• a POI depiction image set comprising a plurality of depiction images that depict the POI from a respective plurality of angles and/or positions;
• and
• a path image set comprising a plurality of path images that collectively depict a path from a starting location to an ending location within the POI;
• performing a quality verification process for at least some of the plurality of image sets;
• responsive to performing the quality verification process, transmitting capture information to the computing system, wherein the capture information comprises the plurality of image sets for the POI;
• and
• obtaining, from the computing system, video data that depicts a virtual camera traversing the path from the starting location to the ending location within the POI, wherein the video data is generated by the computing system using a machine-learned POI representation model that is trained to generate a representation of the POI based on the plurality of image sets.

One or more tangible, non-transitory computer readable media storing computer-readable instructions that when executed by one or more processor devices cause the one or more processor devices to perform operations, the operations comprising:

• causing capture information to be sent to a user computing device, wherein the capture information comprises instructions to a user of the user computing device to capture a plurality of image sets for a Point of Interest (POI), and wherein the instructions indicate that a distance, between the user computing device and surfaces of the POI, from which to capture the plurality of image sets is greater than a threshold distance;
• receiving, from the user computing device, the plurality of image sets for the POI, wherein the plurality of image sets comprises:
• a calibration image set comprising a plurality of calibration image pairs, each of the calibration image pairs comprising two calibration images captured at two different locations within the POI that are separated by a pre-defined distance;
• a POI depiction image set comprising a plurality of depiction images that depict the POI from a respective plurality of angles and/or positions;
• and
• a path image set comprising a plurality of path images that collectively depict a path from a starting location to an ending location within the POI;
• training a machine-learned POI representation model with the plurality of image sets for the POI, wherein the machine-learned POI representation model is trained to generate a representation of the POI;
• and
• using the machine-learned POI representation model to generate video data that depicts a virtual camera traversing the path from the starting location to the ending location within the POI.