VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection.
Zihua LiuHiroki SakumaMasatoshi OkutomiPublished in: CoRR (2024)
Keyphrases
- d objects
- weakly supervised
- object class
- object classes
- object detectors
- object recognition
- geometric models
- three dimensional
- viewpoint
- multi view
- object detection
- pose estimation
- topic models
- relation extraction
- multiple views
- superpixels
- bounding box
- semi supervised
- computer vision
- machine learning
- object model
- co occurrence
- image features