Detailed 3D Human Body Reconstruction from Multi-view Images Combining Voxel Super-Resolution and Learned Implicit Representation.
Zhongguo LiMagnus OskarssonAnders HeydenPublished in: CoRR (2020)
Keyphrases
- human body
- super resolution
- high resolution
- image reconstruction
- three dimensional
- low resolution
- pedestrian detection
- depth map
- multi frame
- pose estimation
- motion estimation
- single image
- high quality
- depth information
- multi view
- image representation
- d objects
- reconstruction method
- articulated objects
- maximum a posteriori
- field of view
- viewpoint
- test images
- image patches