Google Reconstructs Pelé’s Lost 1959 Goal

On August 2, 1959, Pelé scored what he called the greatest goal of his career: three consecutive sombreros over defenders, a knee flick past the goalkeeper, and a header into the net—without the ball touching the ground. No camera captured it.

For 67 years, the “Gol da Rua Javari” survived only in the memories of fans who witnessed it. Google DeepMind has now reconstructed the sequence in partnership with Pelé’s family and the Pelé Brand.

Historian Anita Lucchesi assembled nearly 2,000 historical records, including stadium blueprints and family albums, and interviewed surviving eyewitnesses. A production crew then filmed live-action footage at the original Rua Javari stadium, using period-accurate leather balls and uniforms.

The footage was processed with three Google models:

Recommended reading

Face AI speeds up video face swaps

• Veo 3 for video generation
• Gemini Omni for conversational video generation
• Nano Banana Pro for precision image generation

The models replaced the stunt player with Pelé’s likeness, restyled the modern stadium to reflect its 1959 architecture and weather, and generated period-appropriate crowd scenes. The final footage was run through a filmout machine to recreate the look of 1950s cinema, then finished with traditional visual effects for ball compositing and color grading.

“He would be so proud to see all this happening. He’d always say it was a shame that the goal was never recorded,” said Flávia Kurtz, Pelé’s daughter.

The reconstruction is now on display at the Pelé Museum in Santos. Google launched Gemini Omni as a conversational video-generation model at I/O 2026, and describes the Pelé project as its most culturally significant application to date.

Rather than generating an entirely fictional scene, the project rebuilds a real event from fragmented evidence. That makes it an unusual example of generative video being used for cultural preservation instead of simply producing new synthetic content.