用大核注意力提升单目深度估计的细节精度
Self-supervised Monocular Depth Estimation with Large Kernel Attention
- 设计大核注意力解码器，保持特征二维结构
- 引入上采样模块恢复深度图细粒度信息
- 自监督训练，在KITTI上表现优异
自监督单目深度估计因其无需标注数据而受到关注。现有方法多结合卷积与Transformer以建模长距离依赖，但传统Transformer将2D图像特征视为1D序列，虽通过位置编码部分缓解空间信息损失，仍易忽略通道特征，限制深度估计性能。本文提出一种基于大核注意力的自监督单目深度估计网络，可建模长距离依赖且不破坏特征的二维结构，同时保持通道自适应性。此外，引入上采样模块以精准恢复深度图中的细粒度细节。实验表明，该方法在KITTI数据集上达到具有竞争力的性能。
原文摘要 · Abstract (English)
Self-supervised monocular depth estimation has emerged as a promising approach since it does not rely on labeled training data. Most methods combine convolution and Transformer to model long-distance dependencies to estimate depth accurately. However, Transformer treats 2D image features as 1D sequences, and positional encoding somewhat mitigates the loss of spatial information between different feature blocks, tending to overlook channel features, which limit the performance of depth estimation. In this paper, we propose a self-supervised monocular depth estimation network to get finer details. Specifically, we propose a decoder based on large kernel attention, which can model long-distance dependencies without compromising the two-dimension structure of features while maintaining feature channel adaptivity. In addition, we introduce a up-sampling module to accurately recover the fine details in the depth map. Our method achieves competitive results on the KITTI dataset.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。