Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth

Exploiting geometric features is a common approach to enhance monocular 3D object detection. However, their performance is limited due to the absence of depth information. To address this limitation, an external depth estimator can be employed to predict depth, but this approach significantly reduces the efficiency and flexibility of the model. Instead of relying on a costly depth estimator, we propose a depth-aware monocular 3D object detector that is trained using augmented training data. Specifically, we utilise reference images and their corresponding depth maps to train an efficient rendering module, which synthesises a variety of photo-realistic images with different virtual depths. By learning from these images, the detector adapts its features to depth variations. Furthermore, we introduce an auxiliary module that guides the network to learn more informative representations from the depth images. Both modules are removed after training, resulting in no additional computational overhead during the final deployment.