DCT

8:25-cv-00576

Pointivo Inc v. 5x5 Tech Inc

Log In

I. Executive Summary and Procedural Information

  • Parties & Counsel:
  • Case Identification: 8:25-cv-00576, M.D. Fla., 03/10/2025
  • Venue Allegations: Plaintiff alleges venue is proper in the Middle District of Florida because Defendant maintains an established and regular place of business in St. Petersburg, Florida, from which it allegedly commits acts of patent infringement.
  • Core Dispute: Plaintiff alleges that Defendant’s Ávrio AI-powered software platform infringes five U.S. patents related to photogrammetric methods for creating and analyzing 3D models from 2D images.
  • Technical Context: The technology at issue involves using computer vision and artificial intelligence to process imagery, often captured by drones, to generate accurate 3D models and "digital twins" of physical assets for inspection and measurement.
  • Key Procedural History: The complaint does not mention any prior litigation, Inter Partes Review (IPR) proceedings, or licensing history related to the asserted patents.

Case Timeline

Date Event
2014-10-22 Priority Date for U.S. Patent Nos. 9,460,517 & 9,886,774
2016-01-29 Priority Date for U.S. Patent No. 9,904,867
2016-10-04 U.S. Patent No. 9,460,517 Issues
2017-01-28 Priority Date for U.S. Patent No. 11,043,026
2018-02-06 U.S. Patent No. 9,886,774 Issues
2018-02-27 U.S. Patent No. 9,904,867 Issues
2019-12-01 Priority Date for U.S. Patent No. 11,935,288
2021-06-22 U.S. Patent No. 11,043,026 Issues
2024-03-09 U.S. Patent No. 11,935,288 Issues
2025-03-10 Complaint Filed

II. Technology and Patent(s)-in-Suit Analysis

U.S. Patent No. 9,460,517: Photogrammetric Methods And Devices Related Thereto (Issued Oct. 4, 2016)

The Invention Explained

  • Problem Addressed: The patent addresses the challenge of obtaining accurate measurements from photographs of objects using passive photogrammetry, noting that existing methods were often cumbersome, prone to user error, or required specialized, multi-camera hardware not typically found on mobile devices (U.S. Patent No. 9,460,517, col. 1:19-2:18).
  • The Patented Solution: The invention describes methods for generating accurate 3D digital representations from a series of overlapping 2D images captured by a single, passive image-capture device, such as a standard video camera on a mobile phone (’517 Patent, Abstract). It uses "structure from motion" algorithms to process these images, create the 3D model, and then allow a user or computer to select and extract specific measurements from that model (’517 Patent, col. 3:1-12).
  • Technical Importance: This approach aimed to make accurate 3D modeling and measurement more accessible by leveraging the single cameras already ubiquitous on mobile devices, reducing the need for specialized hardware or complex manual calibration procedures (’517 Patent, col. 2:19-35).

Key Claims at a Glance

  • The complaint asserts independent claim 11 (Compl. ¶33).
  • Claim 11 Elements:
    • A computerized method of obtaining at least one measurement of an object of interest.
    • Receiving a plurality of 2D images of a scene from a single passive image-capture device, where the images include data of the object and are at least partially overlapping.
    • Generating, by a computer, a 3D representation of the object from the 2D images using a process incorporating a structure from motion algorithm.
    • Selecting, by computer or user, one or more dimensions of interest in the object.
    • Extracting data, by the computer, from the 3D representation corresponding to each selected dimension.
    • Processing the extracted data to provide a measurement value for each selected dimension.
  • The complaint does not explicitly reserve the right to assert other claims, but this is standard practice.

U.S. Patent No. 9,886,774: Photogrammetric Methods And Devices Related Thereto (Issued Feb. 6, 2018)

The Invention Explained

  • Problem Addressed: This patent, related to the ’517 Patent, addresses similar problems in creating accurate 3D models from passive imagery, focusing on the specific steps of converting raw image data into structured geometric information (’774 Patent, col. 1:19-2:45).
  • The Patented Solution: The invention describes a method that takes overlapping 2D images from a single passive device and first generates a "3D point cloud" of the object. From this point cloud, the system then generates "primitive geometry information," such as edge points, lines, and planar surfaces. Finally, it converts this geometric information into 3D coordinates, creating a structured model of the object from which measurements can be taken (’774 Patent, Abstract; col. 3:5-24).
  • Technical Importance: The method provides a specific pathway for transforming unstructured point cloud data into structured geometric data, which is a foundational step for creating usable CAD-like models and enabling precise automated analysis (’774 Patent, col. 2:19-45).

Key Claims at a Glance

  • The complaint asserts independent claim 1 (Compl. ¶50).

  • Claim 1 Elements:

    • A computerized method of obtaining at least one measurement of an object of interest.
    • Receiving a plurality of overlapping 2D images from a single passive image-capture device.
    • Generating, by a computer, a 3D point cloud of the object from the image data.
    • Generating information about spatial distances between point pairs in the 3D point cloud, thereby providing "primitive geometry information" (e.g., edge points, lines, surfaces).
    • Converting the generated information into 3D coordinates for the object.

  • The complaint does not explicitly reserve the right to assert other claims.

  • Multi-Patent Capsule: U.S. Patent No. 9,904,867

    • Patent Identification: U.S. Patent No. 9,904,867, "Systems And Methods For Extracting Information About Objects From Scene Information," issued February 27, 2018.
    • Technology Synopsis: This patent describes a method for improving the accuracy of object identification by combining 2D image information with 3D information. The process involves generating "projective geometry information" to link the two data types, clustering the 3D data, segmenting the 2D data, and then iteratively cross-referencing them to create validated information about objects in a scene (Compl. ¶68).
    • Asserted Claims: At least claim 18 is asserted (Compl. ¶67).
    • Accused Features: The Ávrio platform is accused of performing a method of generating information about objects by providing and combining 2D and 3D information, generating projective geometry and clustered 3D information, and iteratively cross-referencing the data to produce validated results (Compl. ¶68).

  • Multi-Patent Capsule: U.S. Patent No. 11,043,026

    • Patent Identification: U.S. Patent No. 11,043,026, "Systems And Methods For Processing 2D/3D Data For Structures Of Interest In A Scene And Wireframes Generated Therefrom," issued June 22, 2021.
    • Technology Synopsis: The patent discloses a method for automatically generating a "wireframe rendering" (a skeletal representation) of a structure. The process involves providing 2D and 3D data, processing it to generate an edge or skeletal representation, and then extracting "geometric primitives" (e.g., planes, cylinders, cones) from that representation to build the final wireframe (U.S. Patent No. 11,043,026 B1, Abstract; Compl. ¶85). The patent specification explicitly lists the canonical expressions for these primitives (’026 Patent, col. 8:1-13; Table 1).
    • Asserted Claims: At least claim 1 is asserted (Compl. ¶84).
    • Accused Features: The Ávrio platform is accused of generating wireframe renderings by providing 2D and 3D data, generating a skeletal representation, extracting geometric primitives from a list corresponding to that in the patent, and processing the output to create the wireframe (Compl. ¶¶ 85-86).

  • Multi-Patent Capsule: U.S. Patent No. 11,935,288

    • Patent Identification: U.S. Patent No. 11,935,288, "Systems And Methods For Generating Of 3D Information On A User Display From Processing Of Sensor Data For Objects, Components Or Features Of Interest In A Scene And User Navigation Thereof," issued March 9, 2024.
    • Technology Synopsis: This patent describes a method for remotely inspecting an object by providing a user with a dynamic, multi-data-type display. The system uses a stored data collection (including 2D aerial images from a UAV) and generates an "object information display" in a single viewport that includes a 3D representation and at least one other synchronized data type. The user can navigate a virtual "scene camera" relative to the 3D model, and the display updates in real time to show an object-centric visualization (U.S. Patent No. 11,935,288 B2, Abstract; Compl. ¶101).
    • Asserted Claims: At least claim 1 is asserted (Compl. ¶100).
    • Accused Features: The Ávrio platform is accused of performing a method of remote inspection by providing a stored data collection including UAV images, generating a display with a 3D representation and other synchronized data types, and allowing a user to navigate a scene camera to update the display in real time (Compl. ¶101).

III. The Accused Instrumentality

  • Product Identification: The accused instrumentality is "Ávrio, an AI-powered software platform, along with related products and services" offered by Defendant 5x5 Technologies, Inc. (Compl. ¶24).
  • Functionality and Market Context: The complaint alleges that the Ávrio platform is a system for AI-driven 3D image analytics used for asset inspection, monitoring, and management (Compl. ¶¶ 15-16, 24). Based on the infringement allegations, the accused functionality includes receiving 2D images of a scene (e.g., from a drone), processing those images using algorithms to generate 3D representations such as point clouds and wireframes, extracting measurements and geometric information from these models, and providing an interactive user display for navigating and analyzing the combined 2D and 3D data (Compl. ¶¶ 34, 51, 68, 85, 101). Plaintiff positions its own technology and the accused technology in the market of "automated asset inspection and digital twin technology" (Compl. ¶19).

IV. Analysis of Infringement Allegations

The complaint references claim chart exhibits (Exhibits A-E) that are not attached to the publicly filed document; therefore, the infringement allegations are summarized below in prose based on the complaint's narrative descriptions.

’517 Patent Infringement Allegations
The complaint alleges that the Accused Products perform a method of obtaining measurements by receiving multiple overlapping 2D images of a scene from a single passive device, generating a 3D representation of an object using a structure from motion algorithm, allowing for selection of dimensions of interest, and extracting measurement values from the 3D model (Compl. ¶34).

’774 Patent Infringement Allegations
The complaint alleges the Accused Products infringe by performing a method that receives overlapping 2D images from a single passive device, generates a 3D point cloud from that image data, generates "primitive geometry information" by analyzing spatial distances within the point cloud, and converts this information into 3D coordinates for the object of interest (Compl. ¶51).

No probative visual evidence provided in complaint.

  • Identified Points of Contention:
    • Scope Questions: A central question for both the ’517 and ’774 Patents may be the scope of "a single passive image-capture device." The patents appear to contemplate a single device like a mobile phone camera creating a video stream (’517 Patent, col. 4:3-6). The infringement analysis may turn on whether the accused Ávrio platform's data ingestion process, which may involve images from a drone flight, meets this limitation as understood in the context of the patent.
    • Technical Questions: The infringement theories depend on the specific algorithms used by the Ávrio platform. A key factual question will be whether Ávrio's process for creating 3D models is one "incorporating a structure from motion algorithm" as required by the ’517 Patent, and whether its process for analyzing point clouds constitutes "generating... primitive geometry information" by analyzing "spatial distances between point pairs" as claimed by the ’774 Patent. The evidence presented regarding the internal workings of the Ávrio software will be critical.

V. Key Claim Terms for Construction

’517 Patent (Claim 11)

  • The Term: "a single passive image-capture device"
  • Context and Importance: This term is foundational to the claimed method, distinguishing it from multi-camera stereo systems. The dispute may focus on whether a series of images taken during a single drone flight, potentially over minutes and from varying locations, constitutes capture from a "single" device in the manner contemplated by the patent, or if it functions more like a collection of distinct captures.
  • Intrinsic Evidence for Interpretation:
    • Evidence for a Broader Interpretation: The specification mentions the device could be a "video camera" (’517 Patent, col. 10:5-7), which inherently captures a sequence of images over time from different positions. This may support an interpretation that covers a continuous or semi-continuous data capture session.
    • Evidence for a Narrower Interpretation: The background of the patent contrasts the invention with systems that use "two or more photographic images taken from different positions" (’517 Patent, col. 1:20-22). A defendant may argue this context suggests the "single device" innovation is tied to a more constrained or localized capture process, such as a person taking a brief video while walking around an object.

’774 Patent (Claim 1)

  • The Term: "primitive geometry information"
  • Context and Importance: This term defines the type of data generated from the 3D point cloud and is a crucial intermediate step in the claimed method. Its definition will determine what kind of data processing satisfies this limitation. Practitioners may focus on this term because its definition appears to be a central part of the claimed invention.
  • Intrinsic Evidence for Interpretation:
    • Evidence for a Broader Interpretation: The claim itself provides a non-exhaustive list: "comprising information about edge/boundary points, straight lines, curved boundaries, planar surfaces or curved surfaces" (’774 Patent, col. 11:1-3). This "comprising" language suggests the term is not limited to only those examples.
    • Evidence for a Narrower Interpretation: The detailed description does not appear to provide a specific, explicit definition beyond the examples listed in the claim. A party could argue that the term should be limited to the types of fundamental geometric elements enumerated, rather than encompassing more complex or abstract structural information.

VI. Other Allegations

  • Indirect Infringement: For each asserted patent, the complaint alleges both induced and contributory infringement. Inducement is based on allegations that the Defendant provides customers with instructions, advertising, and technical support that intentionally cause them to use the Ávrio platform in an infringing manner (e.g., Compl. ¶¶ 35, 52). Contributory infringement is based on allegations that the Accused Products have "special features" that are not staple articles of commerce and have no substantial non-infringing uses (e.g., Compl. ¶¶ 36, 53).
  • Willful Infringement: The complaint alleges willful infringement of all asserted patents. The allegations are based on Defendant’s alleged knowledge of the patents as of the filing of the lawsuit, and on an "information and belief" allegation that Defendant maintains a "policy or practice of not reviewing the patents of others," which Plaintiff characterizes as willful blindness (e.g., Compl. ¶¶ 37-40, 54-57).

VII. Analyst’s Conclusion: Key Questions for the Case

  • A core issue will be one of technical implementation: Do the specific algorithms and data processing workflows within the accused Ávrio platform perform the steps recited in the asserted claims? The case will likely require a detailed, step-by-step comparison between the patented methods and the actual operation of the accused software, turning on expert analysis of source code and system architecture.
  • A second key question will be one of definitional scope: Can claim terms rooted in the patents' 2014-2019 priority dates, such as "a single passive image-capture device" and "primitive geometry information," be construed to cover the potentially more complex data ingestion and analysis techniques of a modern AI-powered platform? The construction of these terms will be central to determining the boundaries of the patents' exclusionary rights.
  • A third question will be one of patent eligibility and validity: The complaint preemptively asserts that the claims are not directed to abstract ideas (e.g., Compl. ¶29). A likely defense will challenge the patents under 35 U.S.C. § 101, raising the question of whether the claimed methods represent a patent-eligible improvement to computer functionality or are merely abstract processes of data gathering and analysis performed on a generic computer.