.png){kind=icon}
.png){kind=icon}
Return
Uncertain Object Representation for Image-Based 3D Object Perception
.png){kind=icon}
PRE
AI
DOI：10.1109/TPAMI.2025.3568120.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Due to the ill-posed nature of locating 3D objects based on image inputs, objects detected by camera-based detectors tend to have considerable uncertainty in their localization. Previous works in camera-based 3D detection and tracking represent each detected object as a single certain 3D bounding box, ignoring their localization uncertainty. We propose the uncertain representation of 3D objects to meet the indeterminacy of localizing objects in images. We model the localization uncertainty of objects during the detection process and represent the location of objects as a probability distribution in 3D space. For camera-based 3D detection, we propose to gather and suppress redundant predictions about an object to form its uncertain representation. For camera-based 3D multiple object tracking, we generalize the cross-frame association metric under the uncertain representation of objects for better-tracking objects with uncertain and unstable localization. As a plug-in module for camera 3D detectors, our proposed method brings a +3.5%/+3.2%/+3.7% NDS boost to BEVDet4D/BEVDet4D-Depth/DD3D on nuScenes validation set and a +4.7% NDS boost to BEVDet4D-Depth on nuScenes test set. With enhanced cross-frame association, our tracking method achieves a 48.2% AMOTA performance and reduces the remaining identity-switch cases to only 300 on nuScenes test set.
Keywords:
Camera-based 3D detection
camera -based 3D multi-object tracking (3DMOT)
uncertainty
object representation
Journal
IF:
18.6
Papers:
831
Citations:
9.8W