computer-vision

From photons to 3D geometry: the pinhole model, intrinsic matrix K, lens distortion, feature matching, stereo depth, and where CNNs help (and fail) in robot perception pipelines.

Understand why fully-connected layers fail at image scale, then build up the CNN toolkit: convolutions, kernels, stride, padding, feature maps, pooling, and parameter sharing. Finish with the ResNet residual connection idea that unlocked networks of 100+ layers.