Dense Multimodal Alignment for Open-Vocabulary 3D Scene Understanding.
Ruihuang LiZhengqiang ZhangChenhang HeZhiyuan MaVishal M. PatelLei ZhangPublished in: CoRR (2024)
Keyphrases
- d scene
- scene flow
- view dependent
- flow estimation
- single image
- depth map
- image based rendering
- planar surfaces
- scene understanding
- optical flow
- camera parameters
- scene geometry
- scene structure
- view synthesis
- camera viewpoint
- scene flow estimation
- photorealistic
- data sets
- indoor scenes
- ego motion
- motion field
- coordinate frame
- input image
- object recognition
- image sequences