ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance.
Ziyu GuoYiwen TangRenrui ZhangDong WangZhigang WangBin ZhaoXuelong LiPublished in: CoRR (2023)
Keyphrases
- multi view
- single view
- multiple views
- d objects
- camera calibration
- multiple cameras
- depth map
- three dimensional
- multi view clustering
- scene flow estimation
- semi supervised
- multiple viewpoints
- multi view stereo
- surface reconstruction
- depth video
- multi view face detection
- co training
- multi view reconstruction
- view synthesis
- range images
- prior knowledge
- free viewpoint
- multi view learning
- face tracking