Task-Aware Monocular Depth Estimation for 3D Object Detection
Xinlong Wang, Wei Yin, Tao Kong et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 2020
Monocular depth estimation enables 3D perception from a single 2D image, thus attracting much research attention for years. Almost all methods treat foreground and background regions (“things and stuff”) in an image equally. However, not all pixels are equal. Depth of foreground objects plays a crucial role in 3D object recognition and localization. To date how to boost the depth prediction accuracy of foreground objects is rarely discussed. In this paper, we first analyze the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the foreground and background depth using separate optimization objectives and decoders. Our method significantly improves the depth estimation performance on foreground objects. Applying ForeSeE to 3D object detection, we achieve 7.5 AP gains and set new state-of-the-art results among other monocular methods. Code will be available at: https://github.com/WXinlong/ForeSeE.
Cited by 73 works. doi:10.1609/aaai.v34i07.6908 Open-access PDF
Authors
References
- Deep Residual Learning for Image Recognition
- ImageNet classification with deep convolutional neural networks
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Aggregated Residual Transformations for Deep Neural Networks
- Vision meets robotics: The KITTI dataset
- Indoor Segmentation and Support Inference from RGBD Images
- Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
- Make3D: Learning 3D Scene Structure from a Single Still Image
- Recovering Surface Layout from an Image
- Frustum PointNets for 3D Object Detection from RGB-D Data