AI & 3D Glossary

Computer vision is a field of artificial intelligence that trains machines to interpret and understand visual information from cameras, images, and video - enabling automated detection, tracking, segmentation, and scene understanding.

3D generative AI uses deep learning models to automatically create three-dimensional assets - meshes, textures, and scenes - from text prompts, images, or other conditioning inputs, dramatically accelerating 3D content workflows.

Gaussian splatting is a real-time 3D scene representation that models a scene as millions of small 3D Gaussian primitives, each with a position, covariance, colour, and opacity - enabling photorealistic rendering at interactive frame rates without neural network inference.

A Neural Radiance Field (NeRF) is a neural network that learns a continuous volumetric scene representation from a set of posed images, mapping every 3D position and viewing direction to a colour and density - enabling photorealistic novel-view synthesis.

A point cloud is an unstructured set of 3D points - each defined by (x, y, z) coordinates and optionally colour, intensity, or normals - captured by LiDAR sensors, depth cameras, or photogrammetry, serving as a raw spatial representation of a physical scene or object.

Object detection is a computer vision task that identifies and localises objects within an image or video frame by predicting bounding boxes and class labels - enabling machines to understand what objects are present and where they are.

Retopology is the process of rebuilding the surface mesh of a 3D model with cleaner, more efficient polygon topology - converting dense, irregular scans or sculpts into production-ready meshes with proper edge flow, UVs, and controllable polygon count.

MLOps (Machine Learning Operations) is the set of practices, tools, and infrastructure for deploying, monitoring, and maintaining machine learning models in production - bridging the gap between model development and reliable, scalable operation.

A digital twin is a virtual replica of a physical object, environment, or system - continuously synchronised with real-world data - used for monitoring, simulation, analysis, and decision-making across its lifecycle.

LiDAR (Light Detection and Ranging) is a remote sensing technology that measures distances by emitting laser pulses and recording their return time - producing dense, accurate 3D point clouds of the surrounding environment.