3 Sources
[1]
Google used Veo and Gemini to reconstruct the greatest goal Pelé ever scored, which was never filmed
Google DeepMind reconstructed Pelé's 1959 "lost goal" using Veo, Gemini Omni, and Nano Banana Pro. 2,000 records and eyewitness interviews informed the project. It is on display at the Pelé Museum. 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, all without the ball ever touching the ground. It was never filmed. For 67 years, the "Gol da Rua Javari" existed only in the memories of the fans who were there. Google DeepMind has now reconstructed it. The project, built in partnership with Pelé's family and the Pelé Brand, combined traditional filmmaking with three Google AI models: Veo 3, Gemini Omni, and Nano Banana Pro. Historian Anita Lucchesi gathered nearly 2,000 historical records, from stadium blueprints to family albums, and interviewed surviving eyewitnesses. A crew then shot live-action footage at the original Rua Javari stadium using period-accurate leather balls and uniforms. The footage was fed into the AI models, which replaced the stunt player with Pelé's likeness, restyled the modern stadium to match 1959 architecture and weather, and generated period-appropriate crowd scenes. "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 the Pelé project is its most culturally significant application to date, demonstrating that AI video generation can serve preservation rather than just content production. The final output was run through a filmout machine to capture the look of 1950s cinema, then refined with traditional VFX for ball compositing and colour grading. Nano Banana Pro was designed for precision image generation, and the Pelé reconstruction shows the model working at its most ambitious: not generating content from nothing, but rebuilding a real event from fragments of evidence. In a year when AI has mostly been used to flood the internet with synthetic content, this is a rare case of it being used to recover something real that was lost.
[2]
AI Recreates the Goal Pelé Said Was His Greatest Ever But Wasn't Filmed
Google's DeepMind lab has recreated Pelé's so-called lost goal -- a strike that the iconic Brazilian soccer player said was his best-ever but was never captured on video. It was August 2, 1959, and Pelé's team, Santos, was playing against Clube Atlético Juventus at the Javari Stadium in São Paulo, Brazil. Much to the amazement of the gathered fans, Pelé performed three straight sombrero flicks past the defenders, before executing a knee flick to take it past the goalkeeper, and finally heading the ball into the empty net. Pelé, who reportedly scored thousands of goals in his career, called this one his best-ever goal, which makes it all the more galling that it was never filmed. A photographer did manage to capture a shot of Pelé heading the ball as the opposition defenders looked on. Google used that photo, taken by Raphael Herrera, as one of many prompts into a complex web of AI models. The team sought historical accuracy by speaking to people who had witnessed the goal. They used Gemini Omni, a multimodal AI model, to create an accurate picture of what it was like in 1959 São Paulo. But to really recreate the goal Pelé scored that day, Google sent a film crew to Javari Stadium -- which is still standing in São Paulo's Mooca neighborhood -- and hired local actors to don 1950s soccer jerseys. For movies or video games, actors typically wear motion-cap suits. Instead of that, Google used a model called Performance Control, which takes an input video and produces 3D blue-mesh renderings of the people in the video. Performance Control then uses that data to transfer the motion of the players onto the AI video. As well as wearing the same jerseys, the team also sourced a leather ball, which was the type of ball made out of heavier materials in the mid-20th century. "All these AI tools, they're such amplifiers of our imagination," says Tom Murray, a research engineer at Google DeepMind. "It allows us to really explore and experiment in a way we've just never been able to." The resulting AI footage, which starts at 6:50 in the video above, is the best depiction of Pelé's wonder goal that isn't the Raphael Herrera photograph. It is now on display at the Pelé Museum in Santos. Recreating events that were never recorded is an intriguing use case for AI; a few years back, photojournalist Michael Christopher Brown used AI to imagine pictures of Cubans fleeing to the U.S.
[3]
Google's AI just recreated the best goal ever by Pele that was never actually filmed
My heart is full after watching the clip, and it will bring tears of joy to every true football fan. If you look at the AI landscape, a majority of its usage in the film and television industry has been pretty controversial. Bringing dead actors to life on a screen, using AI to record vintage songs that were never completed, or just using it to film scenes or handle any other part of the creative process -- the backlash has been pretty vocal. But there are a few slivers of hopeful AI usage, too, and Google just delivered one of those in a heartwarming fashion using Gemini AI. I wonder the world never archived This is how the story goes. In 1959, Brazilian football legend Pele scored a goal. And in his own words, it was the best goal of his career. The "Black Pearl" pulled off three consecutive sombreros past the defenders, performed a knee flick past the goalkeeper, and then headed the ball into the net. Getting past multiple opponents, without the ball ever touching the ground, and finishing it off without a perfect header. It's something you rarely ever see, even at the highest levels of professional football. The problem? It was never filmed. The "Gol da Rua Javari" was only witnessed by the thousand of fans and other players on the pitch, only a handful of whom are still alive. The only archival memory was an old photogaraph of the header moment. Google's team conducted interviews with people how saw the even in person, some six decades, and pieced together Pele's steps. Then, using photographs of the stadium, fans, and other players on the ground, a vision was developed of how the events unfolded. Recommended Videos Next, Google's team recreated the whole scene with real humans in the same stadium where Pele scored the goal. For accuracy, they even created the heavy leather ball from that era, alongside Pele's dark boots, and even the uniforms. The whole act was mapped, somewhat like motion capture in films, but without any of the specialized dresses and gear involved. The whole foundation was fed into a system, and using Gemini Omni, Nano Banana Pro image generator, and the Google Veo video engine, the captured data was restyled and given a vintage look resembling the old photographs. Characters were replaced (the stunt person wearing the iconic No. 10 jersey was swapped with Pele's digital likeness) and the whole stadium from that fateful match in 1959 was recreated. A feat reanimated from the pages of history "To ensure the generations looked as period accurate as possible, we ran the digital output through a filmout machine, capturing the distinct look and feel of 1950s cinema," Google writes in its blog. It was a lot of work. But the end result is simply stunning. Seeing Pele's legendary goal for the first time in action, the sheer ball skill, and on-field mastery come to life on video is a sight to behold. The fact that it happened with the consent of Pele's family, and with support from footballers, fans, and real historians, is something that seprates it from your usual cash-grab AI deployment. ""He would be so proud to see all this happening. He'd always say it was a shame that the goal was never recorded. So being able to relive it, with all this technology, is amazing." Pele's daughter was quoated as saying.
Share
Copy Link
Google DeepMind has reconstructed the legendary unfilmed goal Pelé called his career-best using Veo, Gemini Omni, and Nano Banana Pro. The 1959 "Gol da Rua Javari" involved three consecutive sombreros, a knee flick past the goalkeeper, and a header—all without the ball touching the ground. Built from 2,000 historical records and eyewitness interviews, the AI-generated footage now displays at the Pelé Museum in Santos.
On August 2, 1959, Pelé scored what he considered the greatest Pelé goal of his career at Rua Javari stadium in São Paulo, Brazil. The "Gol da Rua Javari" featured three consecutive sombreros over defenders, a knee flick past the goalkeeper, and a header into the net—all without the ball ever touching the ground
1
. For 67 years, this legendary unfilmed goal existed only in the memories of fans who witnessed it and a single photograph by Raphael Herrera capturing the header moment2
. Google DeepMind has now completed a historical reconstruction of this lost moment using advanced generative AI tools.
Source: PetaPixel
The project, developed in partnership with Pelé's family and the Pelé Brand, combined traditional filmmaking with three Google AI models: Veo 3, Gemini Omni, and Nano Banana Pro
1
. Historian Anita Lucchesi gathered nearly 2,000 historical records, including stadium blueprints and family albums, while conducting eyewitness interviews with surviving fans who saw the goal decades ago1
. The team used Gemini Omni, a multimodal AI model launched at I/O 2026, to create an accurate picture of what 1959 São Paulo looked and felt like2
. This approach demonstrates how Google AI can serve cultural preservation rather than just synthetic content creation.Google sent a film crew to Javari Stadium, which still stands in São Paulo's Mooca neighborhood, and hired local actors to don period-accurate 1950s soccer jerseys. The team sourced a heavy leather ball matching the type used in the mid-20th century, along with Pelé's dark boots and authentic uniforms
3
. Instead of traditional motion-capture suits, Google used a model called Performance Control, which takes input video and produces 3D blue-mesh renderings of people, then transfers that motion onto the AI video. "All these AI tools, they're such amplifiers of our imagination," says Tom Murray, a research engineer at Google DeepMind. "It allows us to really explore and experiment in a way we've just never been able to".Related Stories
The live-action footage was fed into the AI models, which replaced the stunt player with Pelé's digital likeness, restyled the modern stadium to match 1959 architecture and weather conditions, and generated period-appropriate crowd scenes
1
. To ensure the AI-generated footage looked authentic, the digital output was run through a filmout machine to capture the distinct look and feel of 1950s cinema, then refined with traditional VFX for ball compositing and color grading1
. Nano Banana Pro, designed for precision image generation, worked at its most ambitious level—not generating content from nothing, but rebuilding a real event from fragments of evidence1
.The reconstruction now displays at the Pelé Museum in Santos, with Pelé's daughter Flávia Kurtz stating: "He would be so proud to see all this happening. He'd always say it was a shame that the goal was never recorded"
1
. This project represents the most culturally significant application of Gemini Omni to date, showing that AI video generation can serve preservation purposes1
. In a year when AI has mostly been used to flood the internet with synthetic content, this stands as a rare case of it being used to recover something real that was lost1
. The fact that it happened with the consent of Pelé's family, and with support from footballers, fans, and real historians, separates it from typical AI deployments3
. This approach to recreate Pelé's greatest goal opens possibilities for using AI to preserve other lost cultural moments, suggesting a future where generative AI tools help document history rather than replace human creativity.Summarized by
Navi
[1]
23 Jul 2025•Technology

11 Jun 2026•Technology

15 Oct 2025•Technology

1
Technology

2
Science and Research

3
Science and Research
