Lightweight Monocular Depth Estimation through Guided Decoding
This work addresses efficient depth estimation for embedded systems, offering incremental improvements in speed and accuracy for applications like robotics and autonomous driving.
The paper tackles monocular depth estimation for embedded platforms by introducing a lightweight encoder-decoder architecture with Guided Upsampling Blocks, achieving state-of-the-art accuracy on NYU Depth V2 and KITTI datasets while delivering up to 144.5 fps on NVIDIA Xavier NX.
We present a lightweight encoder-decoder architecture for monocular depth estimation, specifically designed for embedded platforms. Our main contribution is the Guided Upsampling Block (GUB) for building the decoder of our model. Motivated by the concept of guided image filtering, GUB relies on the image to guide the decoder on upsampling the feature representation and the depth map reconstruction, achieving high resolution results with fine-grained details. Based on multiple GUBs, our model outperforms the related methods on the NYU Depth V2 dataset in terms of accuracy while delivering up to 35.1 fps on the NVIDIA Jetson Nano and up to 144.5 fps on the NVIDIA Xavier NX. Similarly, on the KITTI dataset, inference is possible with up to 23.7 fps on the Jetson Nano and 102.9 fps on the Xavier NX. Our code and models are made publicly available.