Phase 04

Computer Vision

From pixels to understanding across image, video, and 3D.

01Image Fundamentals — Pixels, Channels, Color SpacesBuild~45 minutesQuiz 02Convolutions from ScratchBuild~75 minutesQuiz 03CNNs — LeNet to ResNetLearn + Build~75 minutesQuiz 04Image ClassificationBuild~75 minutesQuiz 05Transfer Learning & Fine-TuningBuild~75 minutesQuiz 06Object Detection — YOLO from ScratchBuild~75 minutesQuiz 07Semantic Segmentation — U-NetBuild~75 minutesQuiz 08Instance Segmentation — Mask R-CNNBuild + Learn~75 minutesQuiz 09Image Generation — GANsBuild~75 minutesQuiz 10Image Generation — Diffusion ModelsBuild~75 minutesQuiz 11Stable Diffusion — Architecture & Fine-TuningLearn + Use~75 minutesQuiz 12Video Understanding — Temporal ModelingLearn + Build~45 minutesQuiz 133D Vision — Point Clouds & NeRFsLearn + Build~45 minutesQuiz 14Vision Transformers (ViT)Build~45 minutesQuiz 15Real-Time Vision — Edge DeploymentLearn + Build~75 minutesQuiz 16Build a Complete Vision Pipeline — CapstoneBuild~120 minutesQuiz 17Self-Supervised Vision — SimCLR, DINO, MAELearn + Build~75 minutesQuiz 18Open-Vocabulary Vision — CLIPBuild + Use~45 minutesQuiz 19OCR & Document UnderstandingLearn + Use~45 minutesQuiz 20Image Retrieval & Metric LearningBuild~45 minutesQuiz 21Keypoint Detection & Pose EstimationBuild~45 minutesQuiz 223D Gaussian Splatting from ScratchBuild~90 minutesQuiz 23Diffusion Transformers & Rectified FlowLearn + Build~75 minutesQuiz 24SAM 3 & Open-Vocabulary SegmentationUse + Build~60 minutesQuiz 25Vision-Language Models — The ViT-MLP-LLM PatternLearn + Use~75 minutesQuiz 26Monocular Depth & Geometry EstimationBuild + Use~60 minutesQuiz 27Multi-Object Tracking & Video MemoryBuild~60 minutesQuiz 28World Models & Video DiffusionLearn + Build~75 minutesQuiz

“Stay hungry, stay foolish.”

— Steve Jobs