GeoMan predicts temporally consistent depth and normals for human videos by conditioning an image-to-video diffusion model on first-frame geometry and using a root-relative depth representation.
Photorealistic monocular 3d reconstruction of humans wear- ing clothing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion
GeoMan predicts temporally consistent depth and normals for human videos by conditioning an image-to-video diffusion model on first-frame geometry and using a root-relative depth representation.