SYSTEM AND METHOD FOR TRAINING A MULTI-VIEW 3D OBJECT DETECTION FRAMEWORK

Systems and methods for training multi-view 3D object detection frameworks are disclosed herein. In one example, a method includes the steps of predicting one or more predicted bounding boxes representing one or more objects within multi-view images using a decoder that considers (a) feature embeddings generated from image features from multi-view images, (b) geometric positional encodings that are associated with the feature embeddings, and (c) view-dependent queries, determining a viewpoint equivariance loss based on a comparison of the one or more predicted bounding boxes with one or more ground truth bounding boxes, and adjusting model weights of networks forming the multi-view 3D object detection framework based on the viewpoint equivariance loss.