frontier models
A Third-Person Video Was Lifted Into the Wearer’s View
LEGO generates egocentric video from exocentric footage without relying on a separately rendered intermediate view.
Summary
LEGO generates egocentric video from exocentric footage without relying on a separately rendered intermediate view.
LEGO tackles a view-transfer problem: turning third-person video into a plausible first-person sequence. Its lifting-free design maps exocentric evidence directly into egocentric generation, avoiding an intermediate rendering stage that can compound geometric and appearance errors. The approach is evaluated on generated and captured video, with the goal of preserving action while changing viewpoint. Such synthesis could broaden training data for embodied models, but the output remains generated evidence, not a record of what a wearer actually saw. The paper reports a video-generation method rather than a solved account of hidden objects or precise 3D scene geometry.
Why it matters
LEGO generates egocentric video from exocentric footage without relying on a separately rendered intermediate view.
Limits and context
- Such synthesis could broaden training data for embodied models, but the output remains generated evidence, not a record of what a wearer actually saw.
Key claims
LEGO generates egocentric video from exocentric footage without relying on a separately rendered intermediate view.
Qualification: Such synthesis could broaden training data for embodied models, but the output remains generated evidence, not a record of what a wearer actually saw.
Evidence: source-2026-10-10-016
Sources
- arXiv preprint 2610.12442, original v1arXiv / submitting research authors · primary research
Corrections
No corrections have been recorded for this story.