CountFormer: Multi-View Crowd Counting Transformer.
Hong MoXiong ZhangJianchao TanCheng YangQiong GuBo HangWenqi RenPublished in: CoRR (2024)
Keyphrases
- multi view
- multiple views
- single view
- three dimensional
- depth map
- camera calibration
- d objects
- multi view learning
- bundle adjustment
- range images
- semi supervised
- multi view clustering
- scene reconstruction
- co training
- scene flow estimation
- view synthesis
- camera parameters
- multiple cameras
- face tracking
- multi view stereo
- implicit shape model
- visual hull
- multiple viewpoints
- machine learning
- multi view images
- stereo video