# Reconstructing Pelé’s lost goal

## Executive summary

Google DeepMind utilized advanced AI models like Gemini Omni and Veo to reconstruct Pelé's legendary 'Gol da Rua Javari,' a goal scored on August 2, 1959, that was never filmed. The project highlights the use of AI for cultural preservation, combining historical research (period accuracy in uniforms, location, and equipment) with cutting-edge technology. Technical methods included using Gemini Omni to synthesize images from historical fragments and employing a specialized Performance Control Model to transfer motion onto actors, enabling the recreation of the spectacular play as closely as possible.

## Key takeaways

- The Historical Event: Pelé scored three consecutive 'sombreros' without the ball touching the ground against Juventus at Rua Javari on August 2, 1959. This goal was never captured on film; only photographs and eyewitness accounts exist.
- AI Reconstruction Methodology: The project combined historical research with AI to bring the unfilmed moment to life, addressing technical challenges like period accuracy (e.g., heavy leather balls) and motion transfer.
- Advanced Motion Modeling: To recreate the action, a Performance Control Model was used to transfer motion onto local actors, simulating motion capture without requiring full suits. This allowed for precise reconstruction of the athletic performance.

## Technical details

- AI Models Used: Gemini Omni and Veo were used to transform historical fragments into moving imagery. Gemini Omni was specifically utilized for synthesizing images based on combined historical ingredients (e.g., uniforms, neighborhood details).
- Motion Transfer Technology: A Performance Control Model was developed to transfer motion from input video onto actors, simulating the process of motion capture without physical suits. This enabled the recreation of complex athletic movements.
- Data Fidelity Requirements: Reconstruction required strict adherence to 'period accuracy,' including recreating the original pitch, uniforms, and understanding that early soccer balls were significantly heavier leather models.

## Practical implications

- The technology demonstrates a powerful application of AI and computer vision for cultural preservation and historical education.
- It establishes new standards for how unrecorded or fragmented historical events can be made accessible to modern audiences.
- The use of specialized motion models suggests applications in film, sports analysis, and virtual reality reconstruction.

## Topics

Artificial Intelligence (AI), Computer Vision, Historical Reconstruction, Motion Capture, Cultural Preservation, Build Engineering Processes, Pelé Brand, Museu Pelé in Santos, Brazil

Source: https://www.youtube.com/watch?v=R-Yqes8AotY