2 min readBuilding
Making Noisy F1 Data Move Like a Car
Sepang Vision Lab replays the 2026 Sepang weekend in 3D from public OpenF1 data. Most of the work went into making sparse, jittery positions move like a real car without inventing anything.
Page / 05Journal
Why something was built, the question behind an experiment, what changed along the way and what is still open. The finished work lives in Projects. This is the thinking around it.

2 min readBuilding
Sepang Vision Lab replays the 2026 Sepang weekend in 3D from public OpenF1 data. Most of the work went into making sparse, jittery positions move like a real car without inventing anything.
4 entries
Sepang Vision Lab replays the 2026 Sepang weekend in 3D from public OpenF1 data. Most of the work went into making sparse, jittery positions move like a real car without inventing anything.
2 min readBuilding
Related build · Sepang Vision Lab
I trained and worked as a civil engineer. The move into data happened gradually, through the information the engineering work kept producing, and the way of thinking came with me.
4 min readLearningUpdated
Letting a model judge the data is the obvious approach. QualityPlus keeps it away from the score: deterministic checks produce the score, AI assists with the findings, and a person makes the final call.
3 min readBuildingUpdated
Related build · QualityPlus
Writing and debugging the same kind of ETL logic again and again left me with a question about messy data. FORMA is where I am testing it.
3 min readBuildingUpdated
Related build · FORMA