P2I-NET: Mapping Camera Pose to Image via Adversarial Learning for New View Synthesis in Real Indoor Environments.
Xujie KangKanglin LiuJiang DuanYuanhao GongGuoping QiuPublished in: ACM Multimedia (2023)
Keyphrases
- reference images
- image based localization
- indoor environments
- view synthesis
- line features
- camera pose
- input image
- feature points
- image data
- single image
- image features
- viewpoint
- high quality
- machine learning
- urban environments
- position and orientation
- point correspondences
- image based rendering
- complex scenes
- structure from motion
- depth information
- d scene
- image matching
- multiple views
- depth map
- super resolution
- mobile robot
- high resolution
- computer vision