论文标题
通过指导解码的轻量级单眼估计
Lightweight Monocular Depth Estimation through Guided Decoding
论文作者
论文摘要
我们提出了一个轻巧的编码器架构，用于单眼深度估计，该体系结构专为嵌入式平台而设计。我们的主要贡献是用于构建模型解码器的引导性上采样块（GUB）。 GUB的动机是由引导图像过滤的概念，依靠图像来指导解码器提高特征表示形式和深度图重建，从而获得了高分辨率的结果，并具有细粒度的细节。基于多个GUB，我们的模型优于NYU深度V2数据集的相关方法，而在Nvidia Jetson Nano上交付高达35.1 fps，在NVIDIA Xavier NX上最多可达144.5 fps。同样，在KITTI数据集上，可以推断jetson nano上的23.7 fps，而Xavier NX上的102.9 fps也可以进行推理。我们的代码和模型公开可用。
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.
