Insurance Services Office, Inc.

Methods and apparatus for detecting objects and determining their three-dimensional position and orientation (pose) using imagery or point cloud data, often for navigation, surveying, or environmental understanding.

Processes for creating or manipulating three-dimensional digital representations of objects or environments, including mesh generation, surface fitting, and depth estimation from multiple views.

Automated systems using image processing and artificial intelligence to identify, classify, and assess the extent of damage to structures or objects, supporting maintenance or insurance claims.

Algorithms and hardware optimizations for rapidly identifying and characterizing relevant visual features (e.g., objects, motion, gradients) from images or video streams, often integrating machine learning for feature representation and recognition, with a focus on real-time performance and reduced computational cost.

Techniques for rendering, interacting with, and managing content within augmented or virtual reality environments, including spatial tracking, gaze interaction, and dynamic multi-application display management.

Methods and apparatus for improving the visual fidelity, resolution, or compression efficiency of video signals, often through advanced processing, up-scaling, or neural network-based filters.

Methods and systems for improving the quality of video streams, generating intermediate frames, or continuously locating and following objects within a sequence of images, even under occlusion.

Methods and systems for identifying, extracting, and structuring specific entities, relationships, or insights from text-based documents, often involving techniques like named entity recognition, relation extraction, or summarization.

Development and optimization of novel neural network layers or architectures specifically designed to improve performance or efficiency for computer vision tasks.

Utilizing machine learning, particularly deep learning, to analyze medical data such as images, sensor readings, or physiological signals for disease prediction, diagnosis, or treatment assessment.

Techniques utilizing deep learning models like Generative Adversarial Networks (GANs) or diffusion models to create new images, modify existing ones, or generate synthetic data based on various inputs or conditions.

Techniques and hardware architectures designed to efficiently generate and display complex 3D graphics, particularly for interactive applications like virtual reality, focusing on speed and visual quality.

Techniques for generating human-like text or other content using large pre-trained models, often involving prompt engineering, speculative decoding, or multi-modal inputs for content creation.

Methods and systems for efficiently reducing the size of digital data, often employing adaptive techniques, neural networks, or temporal modeling, to achieve high compression ratios while preserving data quality. Includes entropy coding.

Methods and systems that identify unusual or suspicious patterns in data streams, often leveraging machine learning models trained on normal behavior, to detect threats, faults, or significant events as they occur.

Computational methods for modeling and simulating photolithography processes, including mask design, aerial image generation, and defect prediction for semiconductor manufacturing.

Systems and methods utilizing artificial intelligence, particularly large language models and neural networks, to extract, summarize, generate, or categorize information from unstructured or semi-structured data sources.

Techniques and hardware for autonomous systems to gather and interpret data about their surroundings, including obstacle detection, object recognition, and depth estimation, to inform control decisions.

Using computational design and simulation to optimize the performance characteristics of specific components or materials within a larger engineering system.