Skip to content

DressRecon: Freeform 4D Human Reconstruction from Monocular Video

License

Notifications You must be signed in to change notification settings

jefftan969/dressrecon

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 

Repository files navigation

DressRecon: Freeform 4D Human Reconstruction from Monocular Video

Jeff Tan, Donglai Xiang, Shubham Tulsiani, Deva Ramanan, Gengshan Yang

Abstract: Given a single input video of a human, DressRecon reconstructs a time-consistent 4D body model, including shape, appearance, time-varying body articulations, as well as extremely loose clothing deformation or accessory objects. We propose a hierarchical bag-of-bones deformation model that allows body and clothing motion to be separated. We leverage image-based priors such as human body pose, surface normals, and optical flow to make optimization more tractable. The resulting neural fields can be extracted into time-consistent meshes, or further optimized as explicit 3D Gaussians for high-fidelity interactive rendering.

About

DressRecon: Freeform 4D Human Reconstruction from Monocular Video

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published