CASwin Transformer: A Hierarchical Cross Attention Transformer for Depth Completion
Authors:
- 8 October 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2836-2841
Abstract
LiDARs and RGB cameras are commonly used sensors in autonomous driving vehicles. However, the high-resolution LiDAR is too expensive, limiting its large-scale application in commercial autonomous vehicles. The low-resolution LiDAR is more affordable and it can approximate the perception level of high-resolution LiDAR combined with corresponding images. In this paper, we propose a hierarchical cross-attention Transformer in dual-branch to predict a dense depth map. The hierarchical architecture builds a feature pattern at all scales and the cross-attention modules fuse the features from different modalities at multiple feature levels. Furthermore, we develop a depth refinement stage to amend the dense depth map predicted by the fusion stage. The proposed method is evaluated on the indoor NYUDepthV2 dataset and outdoor KITTI Odometry dataset. The experiments demonstrate its effectiveness and accuracy compared with the present state-of-the-art methods.Keywords
This publication has 18 references indexed in Scilit:
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows2021
- Vision Transformers for Dense Prediction2021
- Linear Inverse Problem for Depth Completion with RGB Image and Sparse LIDAR Fusion2021
- ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving2019
- Self-Supervised Sparse-to-Dense: Self-Supervised Depth Completion from LiDAR and Monocular Camera2019
- Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network2018
- Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image2018
- Sparsity Invariant CNNs2017
- Parse geometry from a line: Monocular depth estimation with partial laser observation2017
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012