---
title: "Reconstructed Slides: Building Conversational Agents — Thor Schaeff and Philipp Schmid, Google DeepMind"
category: "slides"
video_id: "cVzf49yg0D8"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: Building Conversational Agents — Thor Schaeff and Philipp Schmid, Google DeepMind

## Source Video
[Building Conversational Agents — Thor Schaeff and Philipp Schmid, Google DeepMind](https://www.youtube.com/watch?v=cVzf49yg0D8)

## 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/cVzf49yg0D8/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `157.81`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.53`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.41`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `153.41`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.97`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.58`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.05`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-008.jpg]]

- Source frame: `slide-008.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.82`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-009.jpg]]

- Source frame: `slide-009.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.56`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-010.jpg]]

- Source frame: `slide-010.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.52`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-011.jpg]]

- Source frame: `slide-011.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `156.58`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-012.jpg]]

- Source frame: `slide-012.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `153.21`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-013.jpg]]

- Source frame: `slide-013.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `174.11`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-014.jpg]]

- Source frame: `slide-014.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `155.31`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-015.jpg]]

- Source frame: `slide-015.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `178.0`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-016.jpg]]

- Source frame: `slide-016.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.66`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-017.jpg]]

- Source frame: `slide-017.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `175.63`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-018.jpg]]

- Source frame: `slide-018.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `163.29`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-019.jpg]]

- Source frame: `slide-019.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `175.68`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-020.jpg]]

- Source frame: `slide-022.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `157.43`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-021.jpg]]

- Source frame: `slide-023.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `179.61`
![[assets/reconstructed-slides/cVzf49yg0D8/slide-022.jpg]]

- Source frame: `slide-024.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.3`
## Dense Scene-Detected Slide Candidates
- [[youtube-cVzf49yg0D8-dense-slides]]