PIFu for the Real World: A Self-supervised Framework to Reconstruct Dressed Human from Single-View Images.
Zhangyang XiongDong DuYushuang WuJingqi DongDi KangLinchao BaoXiaoguang HanPublished in: CVM (1) (2024)
Keyphrases
- single view
- multi view
- real world
- three dimensional
- polyhedral objects
- input image
- image data
- object recognition
- repetitive structures
- vanishing points
- data sets
- perspective projection
- calibrated cameras
- man made objects
- image retrieval
- urban environments
- repetitive patterns
- machine learning
- surface reconstruction
- aerial images
- co training
- camera pose
- moving objects
- view invariant
- computer vision