System and method for 3d object perception trained from pure synthetic stereo data

A non-transitory computer-readable medium having program code recorded thereon for 3D object perception, the program code being executed by a processor and comprising:

• program code to extract features from each image of a synthetic stereo pair of images;
• program code to generate a low-resolution disparity image based on the features extracted from each image of the synthetic stereo pair of images:
• program code to generate a feature map based on the low-resolution disparity image and one of the synthetic stereo pair of images using a trained neural network;
• and
• program code to generate a perception prediction of a detected 3D object based on the feature map using a perception prediction head.

A system for 3D object perception, the system comprising:

• a stereo feature extraction module to extract features from each image of a synthetic stereo pair of images;
• a disparity image generation module to generate a low-resolution disparity image based on the features extracted from each image of the synthetic stereo pair of images:
• a feature map generation module to generate a feature map based on the low-resolution disparity image and one of the synthetic stereo pair of images using a trained neural network;
• and
• a 3D object perception module to generate a perception prediction of a detected 3D object based on the feature map using a perception prediction head.