awesome-deep-vision

This repository is a curated reading list for anyone who wants to learn about the research behind teaching computers to see and understand images. It was assembled by a group of researchers and collects papers, courses, books, videos, software tools, and tutorials all in one place. The project is no longer actively maintained, but the archive remains a useful snapshot of the field.

The bulk of the list is organized by research topic. There are sections covering how AI systems learn to classify what is in an image, how they detect and locate specific objects, how they track moving objects across video frames, and how they assign a label to every pixel in a scene (called semantic segmentation). Other sections cover reading text in images, estimating how a human body is posed, generating new images, and connecting images to written captions or answering questions about a photo.

Each entry in the list links to the original academic paper and sometimes to code, a project page, or a pre-trained model. The papers come from universities and research labs including Microsoft Research, UC Berkeley, Oxford, NYU, and others. There is no software to install here and nothing to run: this is a reference index, not an application.

Beyond papers, the list points to university courses on the subject, textbooks, recorded talks, and popular software tools that practitioners use when building computer vision systems. It also links to tutorials and blog posts for readers who want gentler introductions.

If you are a researcher, student, or curious reader trying to map out what has been studied in the field of visual AI, this list gives you a structured starting point. Because it is no longer actively maintained, some links may be outdated and newer developments after the last update are not included. The full README is longer than what was shown.