UniM-OV3D: Uni-Modality Open-Vocabulary 3D Scene Understanding with Fine-Grained Feature Representation.
Qingdong HeJinlong PengZhengkai JiangKai WuXiaozhong JiJiangning ZhangYabiao WangChengjie WangMingang ChenYunsheng WuPublished in: CoRR (2024)
Keyphrases
- fine grained
- d scene
- feature representation
- coarse grained
- depth map
- feature extraction
- single image
- face recognition
- low dimensional
- optical flow
- access control
- camera viewpoint
- data lineage
- feature descriptors
- sparse representation
- feature set
- viewpoint
- computer vision
- classification accuracy
- feature space
- image segmentation