---
title: "Reconstructed Slides: Run Frontier AI at Home — Alex Cheema, EXO Labs"
category: "slides"
video_id: "ESbWpPT_9-o"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: Run Frontier AI at Home — Alex Cheema, EXO Labs

## Source Video
[Run Frontier AI at Home — Alex Cheema, EXO Labs](https://www.youtube.com/watch?v=ESbWpPT_9-o)

## Method
This deck is reconstructed from the existing video frame captures by detecting likely slide regions with OpenCV, cropping/upscaling those regions, deduplicating similar crops, and OCRing the cropped slide images locally. It is a cleaner companion to the full-stage frame deck.

## Reconstructed Slides
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `157.81`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.74`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `162.81`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.15`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.44`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `156.42`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.05`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-008.jpg]]

- Source frame: `slide-008.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `158.31`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-009.jpg]]

- Source frame: `slide-009.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `157.2`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-010.jpg]]

- Source frame: `slide-010.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `156.85`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-011.jpg]]

- Source frame: `slide-011.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `169.73`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-012.jpg]]

- Source frame: `slide-012.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.25`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-013.jpg]]

- Source frame: `slide-013.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `152.38`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-014.jpg]]

- Source frame: `slide-014.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `167.1`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-015.jpg]]

- Source frame: `slide-016.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.01`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-016.jpg]]

- Source frame: `slide-017.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `152.4`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-017.jpg]]

- Source frame: `slide-018.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `154.23`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-018.jpg]]

- Source frame: `slide-019.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `152.3`
![[assets/reconstructed-slides/ESbWpPT_9-o/slide-019.jpg]]

- Source frame: `slide-020.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `154.31`
## Dense Scene-Detected Slide Candidates
- [[youtube-ESbWpPT_9-o-dense-slides]]