3D Packing for Self-Supervised Monocular Depth Estimation
Vitor Guizilini, Rareş Ambruş, Sudeep Pillai et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2020
Although cameras are ubiquitous, robotic platforms typically rely on active sensors like LiDAR for direct 3D perception. In this work, we propose a novel self-supervised monocular depth estimation method combining geometry with a new deep network, PackNet, learned only from unlabeled monocular videos. Our architecture leverages novel symmetrical packing and unpacking blocks to jointly learn to compress and decompress detail-preserving representations using 3D convolutions. Although self-supervised, our method outperforms other self, semi, and fully supervised methods on the KITTI benchmark. The 3D inductive bias in PackNet enables it to scale with input resolution and number of parameters without overfitting, generalizing better on out-of-domain data such as the NuScenes dataset. Furthermore, it does not require large-scale supervised pretraining on ImageNet and can run in real-time. Finally, we release DDAD (Dense Depth for Automated Driving), a new urban driving dataset with more challenging and accurate depth evaluation, thanks to longer-range and denser ground-truth depth generated from high-density LiDARs mounted on a fleet of self-driving cars operating world-wide.
Cited by 736 works. doi:10.1109/cvpr42600.2020.00256 Open-access PDF
Authors
References
- Deep Residual Learning for Image Recognition
- ImageNet: A large-scale hierarchical image database
- Adam: A Method for Stochastic Optimization
- Fully convolutional networks for semantic segmentation
- Dropout: a simple way to prevent neural networks from overfitting
- Image quality assessment: from error visibility to structural similarity
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Automatic differentiation in PyTorch
- Vision meets robotics: The KITTI dataset
- Image Super-Resolution Using Deep Convolutional Networks