Computational Photography, an AI-powered Slopendium

cover concept

cover concept · art via reve.com · loops animated with Kling · reload or click for another · animated

Computational Photography, an AI-powered Slopendium

master table of contents — parts, chapters and sections · full collapsible outline →

24 parts · 202 chapters · 136 drafted · blue = drafted, links open the chapter; grey = outline only

show

1.1From Digital to Computational Photography
1.2How to read this book
1. 1.2.1A book for machines, too
1.3How this book was made
1.4What language for computational photography?
1.5Basic intro to digital images
1. 1.5.1The data structure is gloriously simple
2. 1.5.2An image as a function over the plane
3. 1.5.3An image as a discrete array
4. 1.5.4How the array sits in memory, briefly
5. 1.5.5Floats in [0, 1], for now
6. 1.5.6Generating images from scratch
7. 1.5.7Basic point operations
8. 1.5.8Domain operations
9. 1.5.9Neighborhood operations
10. 1.5.10Two-image operations
11. 1.5.11A little fun to finish
1.6Problem sets

2 FUNDAMENTALS OF PHOTOGRAPHY

2.1Light and physics
2.2Pinhole image formation and linear perspective
2.3Lens image formation
1. 2.3.1Single lenses: refraction and Snell's law
2. 2.3.2Thin lens optics
3. 2.3.3Depth of field
2.4Image measurements as integrals
1. 2.4.1The plenoptic function
2. 2.4.2The pixel integral
2.5Sensors: photosites, CCD vs CMOS
1. 2.5.1Photon to number: the photosite
2. 2.5.2CCD versus CMOS
3. 2.5.3Time integration: the exposure
4. 2.5.4Mechanical versus electronic shutter
5. 2.5.5Global, rolling, and readout shutter
6. 2.5.6A taste of modern sensor tricks
7. 2.5.7How far sensors have come
2.6Noise, signal-to-noise ratio and dynamic range
1. 2.6.1Noise sources
2. 2.6.2Signal-to-noise ratio: it's about ratios
3. 2.6.3Dynamic range
2.7Multiple view geometry
1. 2.7.1Two views: stereo and disparity
2. 2.7.2Two-view geometry: epipolar lines, and the essential and fundamental matrices
2.8Human (and animal) vision and color
1. 2.8.1Visual system anatomy:
2. 2.8.2Color
3. 2.8.3So what are the primary colors?
4. 2.8.4Opponent process and the multistage model
5. 2.8.5Light adaptation
6. 2.8.6Lightness constancy
7. 2.8.7Color constancy
8. 2.8.8Contrast
9. 2.8.9Spatial vision
10. 2.8.10Temporal vision
11. 2.8.11Attention and eye movements
12. 2.8.12Perception of color and images
13. 2.8.13Animal eyes
2.9Color technology
1. 2.9.1analysis vs synthesis and non-orthogonality
2. 2.9.2Measuring color
3. 2.9.3Linear vs Gamma vs. log encoding
4. 2.9.4linear (kind of) color spaces
5. 2.9.5Non-linear perceptually-uniform colour space
6. 2.9.6Reproducing color
7. 2.9.7Color management, ICC, and industry standards
8. 2.9.8Sensing color: multiplexing strategies
9. 2.9.9Color appearance models
10. 2.9.10Skin tones
2.10Photography and camera 101
1. 2.10.1Basic photography: exposure settings — shutter, aperture, and ISO
2. 2.10.2Exposure modes, UI, and auto-ISO
3. 2.10.3Focus, autofocus, and depth of field
4. 2.10.4Lenses and focal length
5. 2.10.5Lens filters: polarizers, ND, and graduated ND
6. 2.10.6Keeping the lens clean
7. 2.10.7Image stabilization
8. 2.10.8UI and display
9. 2.10.9Video modes
10. 2.10.10Programmability, or the lack thereof
11. 2.10.11Anatomy of a modern full-frame interchangeable-lens camera
12. 2.10.12Anatomy of cell-phone cameras
13. 2.10.13Camera versus phone
14. 2.10.14Types of cameras
15. 2.10.15Cameras beyond photography
16. 2.10.16A camera's other sensors
17. 2.10.17Flash and lighting
18. 2.10.18The traditional darkroom
19. 2.10.19The digital darkroom: editing software

3 BASIC IMAGE PROCESSING AND ISP

3.1Image representation
1. 3.1.1An image is an array
2. 3.1.2Beyond the pixels: basic metadata and EXIF
3. 3.1.3Float vs 8-bit vs more bits
4. 3.1.4What the numbers actually mean: encoding
5. 3.1.5What the numbers actually mean: color spaces
6. 3.1.6Three kinds of operation
7. 3.1.7How the array sits in memory
8. 3.1.8Pixel coordinate conventions
9. 3.1.9Alpha and extra channels
10. 3.1.10Video and more dimensions
11. 3.1.11Reading a pixel — and falling off the edge
3.2Developing, Testing and Debugging
1. 3.2.1The workflow: build, run, look at the picture
2. 3.2.2Principles
3. 3.2.3Test on inputs you can verify by hand
4. 3.2.4Per-algorithm debug recipes
5. 3.2.5Crashes and bounds
6. 3.2.6Vibe coding: writing image code with an LLM
3.3Point operations
1. 3.3.1Three kinds of operation
2. 3.3.2The point-operation curve
3. 3.3.3Exposure: a multiply in linear light
4. 3.3.4Brightness vs. exposure
5. 3.3.5Contrast: steepen about a pivot
6. 3.3.6Black point, white point, and levels
7. 3.3.7The general tone curve
8. 3.3.8Basic color enhancement: saturation and vibrance
9. 3.3.9Converting to black and white
10. 3.3.10Lookup tables
11. 3.3.11Video color grading
12. 3.3.12Local point operations
3.4Histograms
1. 3.4.1the histogram
2. 3.4.2the histogram depends on the encoding space
3. 3.4.3a histogram is a sampled estimate
4. 3.4.4histogram equalization
5. 3.4.5histogram matching
6. 3.4.6constraining the slope: Ward's histogram-based tone mapping
3.5Global tone mapping
3.6Beauty curves: the camera "look"
1. 3.6.1Why scene-linear looks dull
2. 3.6.2The shape of the curve
3. 3.6.3Highlights: roll off to white, not to a color
4. 3.6.4Saturation, and the rest of the "look"
5. 3.6.5The discipline
3.7Neighborhood operations and convolution
1. 3.7.1Motivation: blur and sharpen
2. 3.7.2Convolution 101
3. 3.7.3The flip: where-from vs. where-to
4. 3.7.4Properties: the impulse, normalization, symmetry, commutativity
5. 3.7.5Nitty-gritty: finite images
6. 3.7.6A blur zoo
7. 3.7.7Separability
8. 3.7.8Gradient and oriented filters
9. 3.7.9Sharpening
10. 3.7.10Non-linear sharpening
11. 3.7.11Is imaging blur usually a shift-invariant convolution?
12. 3.7.12Where this goes next
3.8Fourier
3.9Downsampling and aliasing
3.10Resampling
1. 3.10.1Domain operations: moving pixels around
2. 3.10.2Start with scaling up
3. 3.10.3The naive idea, and why it leaves gaps
4. 3.10.4Loop over the output, use the inverse transform
5. 3.10.5Nearest neighbour
6. 3.10.6Linear interpolation, in 1-D first
7. 3.10.7Bilinear, in 2-D
8. 3.10.8The convolution perspective
9. 3.10.9Better kernels: bicubic and Lanczos
10. 3.10.10Upsampling vs. downsampling: scale the kernel
11. 3.10.11Prefiltering when the transform isn't a clean scale
12. 3.10.12Where this goes next
3.11Pyramids and wavelets
1. 3.11.1Halfway between space and frequency
2. 3.11.2The idea: process an image at many resolutions
3. 3.11.3The Gaussian pyramid
4. 3.11.4The Laplacian pyramid
5. 3.11.5Reconstruction: an exact encoder and decoder
6. 3.11.6Each level is a frequency band
7. 3.11.7What the bands look like on a real image
8. 3.11.8Honest limitations
9. 3.11.9Cousins: wavelets and steerable pyramids
10. 3.11.10Pyramid blending
11. 3.11.11Other applications
12. 3.11.12Multiresolution as a recurring theme
3.12Image metrics
1. 3.12.1Full-reference vs. no-reference
2. 3.12.2why not just L2?
3. 3.12.3PSNR
4. 3.12.4SSIM
5. 3.12.5VDP and HDR-VDP
6. 3.12.6learned metrics
7. 3.12.7The right metric depends on the task
3.13Denoising
1. 3.13.1what is noise?
2. 3.13.2denoising by averaging multiple shots
3. 3.13.3denoising from a single image
4. 3.13.4Spatial averaging and its limits
5. 3.13.5The bilateral filter: averaging by affinity
6. 3.13.6Self-similarity: non-local means and BM3D
7. 3.13.7Denoise color more than brightness
8. 3.13.8noise estimation
9. 3.13.9The limits of denoising
3.14Demosaicking
3.15Auto-exposure and auto white balance
1. 3.15.1Auto-exposure: metering
2. 3.15.2white balance and color constancy
3. 3.15.3Automatic white balance
4. 3.15.4The limits of white balance, and CRI
3.16File formats and compression
1. 3.16.1The big picture: none, lossless, lossy
2. 3.16.2Data versus metadata: EXIF
3. 3.16.3PNG: the format we read from
4. 3.16.4JPEG: compression by perception
5. 3.16.5RAW files: before the cooking
6. 3.16.6HDR formats: more than 8 bits
7. 3.16.7Modern formats
8. 3.16.8Other formats in passing: TIFF and GIF
3.17Recap ISP, non-destructive editing:
1. 3.17.1A basic ISP
2. 3.17.2Pipeline design and tuning
3. 3.17.3The ISP, evolving: traditional → learned → generative
4. 3.17.4Recap 2: non-destructive editing

4 COMPUTATIONAL TOOLS

6 WARPING, MORPHING, AND LAGRANGIAN APPROACHES

7 MATCHING PIXELS AND HUMANS ACROSS SPACE AND TIME

8 SINGLE IMAGE COMPUTATIONAL PHOTOGRAPHY

9 OPTICS, LENSES, AND ABERRATION CORRECTION

10 MULTIPLE EXPOSURE IMAGING

11 MANY IMAGES AND PHOTO COLLECTIONS

11.1Photo Mosaics
1. 11.1.1The tiling-and-matching pipeline
2. 11.1.2Colour correction and avoiding repeats
3. 11.1.3Multi-scale and irregular tilings
4. 11.1.4Why it resolves into the target at a distance
11.2Retrieval
11.3Auto curation
1. 11.3.1Technical quality — the easy rejects
2. 11.3.2Aesthetics — the hard, learned part
3. 11.3.3Grouping, summary, and diversity
11.4Life logging cameras
1. 11.4.1The devices and how they fire
2. 11.4.2The memory-prosthesis reframing
3. 11.4.3The big-data problem passive capture creates
4. 11.4.4Privacy and ethics
11.5Inpainting Using Millions of Photographs
11.6Photo tourism
1. 11.6.1Structure-from-motion on internet collections
2. 11.6.2From reconstruction to experience
3. 11.6.3Lineage
11.7Photobios
1. 11.7.1Align and order the collection
2. 11.7.2Let the data fill the gaps
3. 11.7.3Collection as experience
11.8Pix 2 GPS
1. 11.8.1Geolocation as retrieval over a geotagged corpus
2. 11.8.2The answer is a distribution
3. 11.8.3Mapping the collection itself
4. 11.8.4The learned successors
11.9Personalized priors
1. 11.9.1Personalized restoration
2. 11.9.2Personalizing generative models
3. 11.9.3The bargain and its ethics
11.10Artistic projects with photo collections
1. 11.10.1Statistical collage — Salavon
2. 11.10.2Anticliché camera
3. 11.10.3Pareidolia

13 ADVANCED COMPUTATIONAL PHOTOGRAPHY ON THE BLEEDING EDGE

13.1Exotic / advanced opticsoutline
1. 13.1.1GRIN
2. 13.1.2Metalenses and advanced crazy optics à la Barbastathis (coherent though)
3. 13.1.3Non-linear optics
13.2Coded imaging,outline
1. 13.2.1Wavefront coding
2. 13.2.2Coded aperture
3. 13.2.3Code in time (phase, amplitude)
4. 13.2.4Optical modulators (spatial light modulators): DMD and LCD/LCoS
5. 13.2.5Theorems
6. 13.2.6End-to-end optimization
7. 13.2.7Lensless imaging?
8. 13.2.8Compressive sensing
9. 13.2.9Discuss optical computing
13.3Light field and multi-aperture imagingoutline
1. 13.3.1Multi-aperture imaging
2. 13.3.2Light fields 101
3. 13.3.3Light field cameras
4. 13.3.4Refocusing
5. 13.3.5Aberration correction
6. 13.3.6I want a light field camera
7. 13.3.7Dual pixel autofocus
8. 13.3.8Plus light field in time = high speed
9. 13.3.9Lenticular displays here
10. 13.3.10Side bar: 3D TV, project starline
11. 13.3.11Dave Brady’s gigapixel stuff
13.4Extra sensors and non-visual dataoutline
1. 13.4.1Accelerometer, gyro
2. 13.4.2Sound
3. 13.4.3GPS
4. 13.4.4Compass
5. 13.4.5Near IR
6. 13.4.6Temperature
13.5Computational illuminationoutline
1. 13.5.1Flash / no flash
2. 13.5.2Ramesh’s multiflash
3. 13.5.3Removing flash artifacts
4. 13.5.4Dark flash, (plus Stasi version!)
5. 13.5.5Strobe photography
6. 13.5.6Matting again?
7. 13.5.7Direct/indirect
8. 13.5.8Polarization?
9. 13.5.9Smart flash
10. 13.5.10Computational bounce flash
11. 13.5.11Light domes
12. 13.5.12Tabletop version
13. 13.5.13Drone lighting (computational rim illumination with aerial robots)
14. 13.5.14Lukas multi-illumination
15. 13.5.15Dual photography
16. 13.5.16Intrinsic images with time lapse
17. 13.5.17Structured light scanning
18. 13.5.18Exploiting natural variations
19. 13.5.19Coherent imaging
20. 13.5.20Confocal, Ioannis
21. 13.5.21Schlieren
22. 13.5.22Relighting, shadow removal
23. 13.5.23Reflection removal
24. 13.5.24In general, what to say about intrinsic images?
13.6Computational sensorsoutline
1. 13.6.1Assorted pixels
2. 13.6.2Fuji
3. 13.6.3Depth sensors
4. 13.6.4Time of flight
5. 13.6.5Single-photon sensors (SPAD, avalanche, photon counting)
6. 13.6.6Doppler / velocity imaging
7. 13.6.7Event sensors
8. 13.6.8Lincoln lab sensors
13.7More temporal and Video stuffoutline
1. 13.7.1High-speed cameras
2. 13.7.2Ultra high speed imaging (Velten, etc.)
13.8De-weathering (fog, rain)outline

14 3D AND DEPTH

14.1What "depth" means, and where it comes fromoutline
14.2Monocular depth estimation (one image → depth)outline
14.3Single-image 3-D: tour into the picture, photo pop-up, 3-D Ken Burnsoutline
14.4Multi-view 3-D reconstruction: the classic pipelineoutline
14.5Photos → radiance fields and Gaussian splatting (NeRF, 3DGS)outline
14.6Feed-forward (amortized) 3-D: skip the per-scene optimizationoutline
14.7Re-photographyoutline
14.8The landscape, and is 3-D a "fake task"?outline
14.93-D displaysoutline

15 REVEALING THE INVISIBLE

15.1Near-infrared (NIR) photographyoutline
15.2Accidental camerasoutline
15.3Motion and video magnificationoutline
15.4Visual microphoneoutline
15.5Corner cameraoutline
15.6Active non-line-of-sightoutline
15.7Passive non-line-of-sightoutline
15.8Mm-wave, wifioutline

16 ADJACENT FIELDS AND APPLICATIONS

16.1Modern sensorsoutline
16.2Astrooutline
1. 16.2.1Extreme long exposure
2. 16.2.2Tracking, stacking, and selection (pointers)
16.3X-rayoutline
16.4Medicaloutline
16.5Microscopyoutline
16.6Mm-waveoutline
16.7Music, soundoutline
16.8Fluorescenceoutline
16.9Opto-acousticoutline
16.10Ultrasoundoutline
16.11Aerial imagingoutline
16.12Computer visionoutline
16.13Robotics, drivingoutline

17 HUMAN FACTORS

17.1Human factors and the art of photography
1. 17.1.1Make better photos
2. 17.1.2Typical shooting scenarios
3. 17.1.3Macro photography
4. 17.1.4Special effect photography
5. 17.1.5Fun artsy stuff
6. 17.1.6Perception of art
17.2Ethics of computational photography
17.3Computational models of perceptionoutline
17.4Spatial (and spatio-temporal) visionoutline
17.5User studiesoutline
17.6Accessibility: photography by and for blind usersoutline
1. 17.6.1Blind camera — capture without a sighted operator
17.7The social and personal practice of photographyoutline

18 IMAGE FORENSICS AND AUTHENTICATION

19.1Programmable camerasoutline
19.2Image processing librariesoutline
19.3Lightroom-style raw developersoutline
19.4Photoshop-style editorsoutline
19.5Networking and image transportoutline
19.6Photography programming on phonesoutline

20 PERFORMANCE ENGINEERING AND HALIDE

20.18-bit and fixed-point arithmeticoutline
20.2Algorithmic speedupsoutline
20.3Performance engineering and scheduling (Halide)outline
20.4Hardware backends: GPU, NPU, DSPoutline
1. 20.4.1Karima’s search

21 CONCLUSIONS, DISCUSSION

21.1Recap in contextoutline
1. 21.1.1Modern phones, multiple apertures, pano, HDR+
2. 21.1.2Recap: a modern mirrorless camera
3. 21.1.3Recap: a modern cell phone multi camera
4. 21.1.4Lightroom
5. 21.1.5Photoshop

22.1Refreshers
1. 22.1.1Linear algebra
2. 22.1.2Calculus: derivatives, gradients, integrals
3. 22.1.3Optimization and regression
4. 22.1.4Probability and information theory
5. 22.1.5Machine learning and deep learning
6. 22.1.6Programming: Python, C++, and PyTorch
22.2Problem Set 0 — Environment and C++ basics
1. 22.2.1Summary
2. 22.2.2Installation and Environment Setup
3. 22.2.3C++
4. 22.2.4Submission
22.3Problem Set 1 — Image class, point operations, and color
1. 22.3.1Summary
2. 22.3.2The Image Class
3. 22.3.3Brightness and Contrast
4. 22.3.4More Image Class Methods
5. 22.3.5Colorspaces
6. 22.3.6Spanish Castle Illusion
7. 22.3.7White Balance
22.4Problem Set 2 — Convolution and the bilateral filter
1. 22.4.1Summary
2. 22.4.2Smart Accessor
3. 22.4.3Blurring
4. 22.4.4Denoising using Bilateral Filtering
5. 22.4.5Extra credit
6. 22.4.6Submission
22.5Problem Set 3 — Denoising and demosaicking
1. 22.5.1Summary
2. 22.5.2Denoising from a sequence of images
3. 22.5.3Demosaicing
4. 22.5.4Edge-based green
5. 22.5.5Red and blue based on green
6. 22.5.66.865 only (or 5% Extra Credit): Sergey Prokudin-Gorsky
7. 22.5.7Extra credit (maximum of 10%)
22.6Problem Set 4 — High dynamic range
1. 22.6.1Summary
2. 22.6.2HDR merging
3. 22.6.3Tone mapping
4. 22.6.4Extra credit (10% max)
22.7Problem Set 5 — Resampling, warping, and morphing
1. 22.7.1Summary
2. 22.7.2Resampling
3. 22.7.3Warping and morphing
4. 22.7.4Extra credit
22.8Problem Set 6 — Homographies and manual panoramas
1. 22.8.1Summary
2. 22.8.2Class Morph
3. 22.8.3Homogeneous Coordinates
4. 22.8.4Linear Algebra
5. 22.8.5Warp and Image with a Homography
6. 22.8.6Compute Homography from 4 Pairs of Points
7. 22.8.7Bounding boxes
8. 22.8.8Extra Credit (up to 10% total)
22.9Problem Set 7 — Automatic panoramas
1. 22.9.1Summary
2. 22.9.2Previous Problem Set Code
3. 22.9.3Class Morph
4. 22.9.4Harris Corner Detection
5. 22.9.5Descriptor and correspondences
6. 22.9.6RANSAC
7. 22.9.7Automatic panorama stitching
8. 22.9.8Blending
9. 22.9.9Mini planet
10. 22.9.106.8370: Stitch N Images (6.8371: Extra Credit 5%)
11. 22.9.11Make your own panorama
12. 22.9.12Extra credits (10% max)
22.10Problem Set 8 — Non-photorealistic rendering
1. 22.10.1Summary
2. 22.10.2Paintbrush splatting
3. 22.10.3Painterly rendering
4. 22.10.4Oriented painterly rendering
5. 22.10.5Your image
6. 22.10.6Paper Review (6.865 only)
7. 22.10.7Extra credits
22.11Problem Set 9 — Make-your-own, video, and ethics
1. 22.11.1Summary
2. 22.11.2Make Your Own Assignment
3. 22.11.3Ethical issues in computational photography
4. 22.11.4Assignment Lists
22.12EXIF and image metadata
1. 22.12.1What EXIF is
2. 22.12.2The fields, grouped by what they describe
3. 22.12.3How far to trust it
4. 22.12.4Privacy: the metadata that follows the picture
5. 22.12.5Reading and writing EXIF
22.13DNG: the Digital Negative
1. 22.13.1What DNG is, and the problem it solves
2. 22.13.2Inside the container
3. 22.13.3What the raw payload looks like: mosaic vs linear
4. 22.13.4The color recipe: matrices, profiles, and white balance
5. 22.13.5Opcodes: corrections the decoder must apply
6. 22.13.6Compression, and embedding the original
7. 22.13.7Where you meet DNG: adoption and relatives
8. 22.13.8Trade-offs, and DNG's relation to EXIF
22.14Rendering a raw DNG
1. 22.14.1The pipeline, step by step
2. 22.14.2Where Lightroom's "look" actually comes from
3. 22.14.3What we would ask an Adobe engineer to check
4. 22.14.4Two kinds of DNG, and the special cases
5. 22.14.5Easy mistakes (most of which we made)
22.15Datasets
1. 22.15.1Classification and features
2. 22.15.2Super-resolution
3. 22.15.3Deblurring and restoration
4. 22.15.4Denoising
5. 22.15.5HDR and tone mapping
6. 22.15.6Retouching and enhancement
7. 22.15.7Depth and motion
8. 22.15.8Color and white balance
9. 22.15.9Faces
10. 22.15.10Inpainting, segmentation, and matting
11. 22.15.11Image quality
22.16A camera-feature wish list
1. 22.16.1Exposure, ISO, and dynamic range
2. 22.16.2Bracketing more than exposure
3. 22.16.3Focus and depth of field
4. 22.16.4Computational raw and the sensor
5. 22.16.5Motion data, metadata, and workflow
6. 22.16.6Panorama and multi-shot
7. 22.16.7The interface and the ecosystem
22.17How this book was created
1. 22.17.1Two documents, not one
2. 22.17.2Compiling a section
3. 22.17.3Figures as code
4. 22.17.4Generative imagery: cover art and 3D
5. 22.17.5Verification and review
6. 22.17.6Keeping a long book coherent
7. 22.17.7The toolchain
8. 22.17.8What the machine did, and what it did not
9. 22.17.9Who wrote what: a per-part estimate
22.18The course tutor: a local, book-grounded AI teaching assistant
1. 22.18.1What it is, and what it is for
2. 22.18.2Local-first
3. 22.18.3Grounded in the book: retrieval-augmented generation
4. 22.18.4It links, it shows equations, it shows figures
5. 22.18.5Two front-ends, one core
6. 22.18.6What the instructor sees
7. 22.18.7Privacy and honesty
22.19The semi-automatic grading system
1. 22.19.1The shape (to be confirmed)
2. 22.19.2Automatic versus human (to be confirmed)
3. 22.19.3To be filled in (from the instructor)
22.20Under the hood: prompts, patterns, and verifiers
1. 22.20.1Prompt patterns that made it work
2. 22.20.2The verifier suite
3. 22.20.3Why this is the interesting part

23 BIBLIOGRAPHY

24 MISSING STUFF, BUGS

24.1Tone mapping doesn't have its own chapter. Just an application of edge aware stuff.outline
24.2Denoising by averaging is after basic denoisingoutline
24.3Photomosaics, my self organizing mapsoutline
24.4Rephotographyoutline
24.5Extreme low lightoutline
24.6Perspective disortionoutline
24.7Tilt shift,outline
24.8Connectivityoutline
24.9Misc.outline

Back matter

📖 Glossary 🔠 Acronyms 🔤 Index 📚 Bibliography