Skip to content
Gopi Krishna Tummala

Computer Vision in 2 Minutes Each

How machines learn to see. For the full story, read the computer vision series.

Camera model

A camera projects the 3D world onto a 2D image.

Remember: intrinsics describe the lens (focal length, center); extrinsics describe where the camera sits. Needed whenever images meet 3D.

Go deeper: Module 3: Calibration.

Convolution

Slide a small filter across the image to detect a pattern everywhere.

Picture it: a stencil for “vertical edge” pressed against every spot on the photo.

Remember: early layers learn edges and colors; deeper layers learn textures, parts and objects.

CNN architectures

ModelRemember it as
AlexNet (2012)Deep learning’s ImageNet breakthrough on GPUs
VGGJust stack small 3×3 filters
ResNetSkip connections make 100+ layers trainable
MobileNet / EfficientNetCheap convolutions for phones
ConvNeXtA modernized CNN that matches transformers

Vision transformer (ViT)

Cut the image into patches, treat them like words, run a transformer.

Remember: sees the whole image at once; needs lots of data or pretraining, then scales very well.

Data augmentation

Create variations of training images (flips, crops, color changes) so the model learns what doesn’t matter.

Remember: the cheapest big win in vision; augmentations must preserve the label.

Object detection

Find each object and draw a box around it with a label.

Remember: two-stage detectors (Faster R-CNN) are accurate; one-stage (YOLO) are fast; DETR treats detection as predicting a set of objects with a transformer.

IoU and NMS

IoU measures box overlap; NMS removes duplicate boxes for the same object.

Remember: mAP, the main detection metric, counts a box as correct above an IoU threshold.

Segmentation

TypeOutput
SemanticA class for every pixel (“road,” “car”)
InstanceA separate mask for each object
PanopticBoth at once

Remember: U-Net’s encoder-decoder with skip connections is the classic architecture.

Segment Anything (SAM)

A foundation model that segments whatever you point at, click or box.

Remember: promptable segmentation without task-specific training.

Self-supervised vision

Learn visual features without labels.

Remember: masked autoencoders hide patches and rebuild them; DINO learns features so good that object boundaries appear without supervision.

Depth and 3D

Recover distance from stereo cameras, motion, or a single image with a learned model.

Remember: monocular depth models (Depth Anything) give relative depth; a few known distances fix the scale. Point clouds come from lidar or depth.

NeRF and Gaussian splatting

Reconstruct a 3D scene from photos so you can render new viewpoints.

Remember: NeRF stores the scene in a neural network (slow to render); Gaussian splatting uses millions of small blobs (renders in real time).

Bird’s-eye view

Turn camera views into a top-down map around a vehicle.

Go deeper: Module 6: Perception.

CLIP

Images and captions trained to land close together in one space.

Remember: enables zero-shot classification (“a photo of a dog” vs “a photo of a cat”) and powers text-to-image models.

Vision-language models

A vision encoder plus an LLM that can talk about images.

Remember: vision encoder → small connector → language model.

Go deeper: Qwen3-VL, When AI Sees and Speaks.

Generating images and video

Go deeper: Generative Models cheatsheet.