← Back to curriculum

Phase 04 · 28 lessons

Computer Vision

From pixels to understanding — image, video, 3D, VLMs, and world models.

01Image Fundamentals — Pixels, Channels, Color SpacesLearn 02Convolutions from ScratchBuild 03CNNs — LeNet to ResNetBuild 04Image ClassificationBuild 05Transfer Learning & Fine-TuningBuild 06Object Detection — YOLO from ScratchBuild 07Semantic Segmentation — U-NetBuild 08Instance Segmentation — Mask R-CNNBuild 09Image Generation — GANsBuild 10Image Generation — Diffusion ModelsBuild 11Stable Diffusion — Architecture & Fine-TuningBuild 12Video Understanding — Temporal ModelingBuild 133D Vision — Point Clouds & NeRFsBuild 14Vision Transformers (ViT)Build 15Real-Time Vision — Edge DeploymentBuild 16Build a Complete Vision Pipeline — CapstoneBuild 17Self-Supervised Vision — SimCLR, DINO, MAEBuild 18Open-Vocabulary Vision — CLIPBuild 19OCR & Document UnderstandingBuild 20Image Retrieval & Metric LearningBuild 21Keypoint Detection & Pose EstimationBuild 223D Gaussian Splatting from ScratchBuild 23Diffusion Transformers & Rectified FlowBuild 24SAM 3 & Open-Vocabulary SegmentationBuild 25Vision-Language Models — The ViT-MLP-LLM PatternBuild 26Monocular Depth & Geometry EstimationBuild 27Multi-Object Tracking & Video MemoryBuild 28World Models & Video DiffusionBuild