---
title: "Reconstructed Slides: Real-time Experiments with an AI Co-Scientist - Stefania Druga, fmr. Google Deepmind"
category: "slides"
video_id: "wNH3q9pqn0U"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: Real-time Experiments with an AI Co-Scientist - Stefania Druga, fmr. Google Deepmind

## Source Video
[Real-time Experiments with an AI Co-Scientist - Stefania Druga, fmr. Google Deepmind](https://www.youtube.com/watch?v=wNH3q9pqn0U)

## 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/wNH3q9pqn0U/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `160.12`
![[assets/reconstructed-slides/wNH3q9pqn0U/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.0`
![[assets/reconstructed-slides/wNH3q9pqn0U/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.64`
![[assets/reconstructed-slides/wNH3q9pqn0U/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.76`
![[assets/reconstructed-slides/wNH3q9pqn0U/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `177.03`
![[assets/reconstructed-slides/wNH3q9pqn0U/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.31`
![[assets/reconstructed-slides/wNH3q9pqn0U/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `177.22`
![[assets/reconstructed-slides/wNH3q9pqn0U/slide-008.jpg]]

- Source frame: `slide-008.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `177.49`
![[assets/reconstructed-slides/wNH3q9pqn0U/slide-009.jpg]]

- Source frame: `slide-009.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `177.24`
![[assets/reconstructed-slides/wNH3q9pqn0U/slide-010.jpg]]

- Source frame: `slide-010.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.9`
![[assets/reconstructed-slides/wNH3q9pqn0U/slide-011.jpg]]

- Source frame: `slide-011.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.78`
![[assets/reconstructed-slides/wNH3q9pqn0U/slide-012.jpg]]

- Source frame: `slide-012.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.63`
![[assets/reconstructed-slides/wNH3q9pqn0U/slide-013.jpg]]

- Source frame: `slide-013.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.28`
![[assets/reconstructed-slides/wNH3q9pqn0U/slide-014.jpg]]

- Source frame: `slide-014.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `177.81`
![[assets/reconstructed-slides/wNH3q9pqn0U/slide-015.jpg]]

- Source frame: `slide-015.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `177.86`
![[assets/reconstructed-slides/wNH3q9pqn0U/slide-016.jpg]]

- Source frame: `slide-016.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.5`
![[assets/reconstructed-slides/wNH3q9pqn0U/slide-017.jpg]]

- Source frame: `slide-017.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.37`
## Dense Scene-Detected Slide Candidates
- [[youtube-wNH3q9pqn0U-dense-slides]]