What Is Computer Vision?
Computer vision is the part of AI that gets information out of images and video, such as classifying a photo, detecting objects or outlining them by pixel.
To a computer, an image is a grid of numbers: a 1,000 × 1,000 colour photo is three million of them. Computer vision explained covers how models turn those numbers into answers, from classifying a photo to outlining an object pixel by pixel.
The guides below follow specific designs. The Vision Transformer, from a 2020 Google Research paper, reads an image as a sequence of patches. Segment Anything, from a 2023 Meta AI paper, cuts out an object from a click or a box. Diffusion models create an image by removing noise step by step, an approach introduced in a 2015 paper.
Diffusion Models Explained: How AI Turns Noise Into Images
How diffusion models work: from noise to image step by step, text prompts and guidance, latent diffusion, flow matching, and how Stable Diffusion and Sora use them.
Segment Anything (SAM) Explained: Click-to-Cut-Out AI
What Meta's Segment Anything Model does: prompts, its three-part design, the 1-billion-mask SA-1B dataset, zero-shot results, and SAM 2 for video.
Vision Transformer (ViT) Explained: How an Image Becomes Patches
How the Vision Transformer cuts an image into 16x16 patches and reads them like words, why it needed large datasets, its three sizes, and ViT vs CNN.
Computer Vision Explained: How AI Sees Images
Computer vision explained simply: how a computer reads an image, classification vs detection vs segmentation, how models are trained, uses and limits.
Showing 1–4 of 4 guides