LiteDepth: Digging into Fast and Accurate Depth Estimation on Mobile Devices

by   Zhenyu Li, et al.

Monocular depth estimation is an essential task in the computer vision community. While tremendous successful methods have obtained excellent results, most of them are computationally expensive and not applicable for real-time on-device inference. In this paper, we aim to address more practical applications of monocular depth estimation, where the solution should consider not only the precision but also the inference time on mobile devices. To this end, we first develop an end-to-end learning-based model with a tiny weight size (1.4MB) and a short inference time (27FPS on Raspberry Pi 4). Then, we propose a simple yet effective data augmentation strategy, called R2 crop, to boost the model performance. Moreover, we observe that the simple lightweight model trained with only one single loss term will suffer from performance bottleneck. To alleviate this issue, we adopt multiple loss terms to provide sufficient constraints during the training stage. Furthermore, with a simple dynamic re-weight strategy, we can avoid the time-consuming hyper-parameter choice of loss terms. Finally, we adopt the structure-aware distillation to further improve the model performance. Notably, our solution named LiteDepth ranks 2nd in the MAI AIM2022 Monocular Depth Estimation Challenge, with a si-RMSE of 0.311, an RMSE of 3.79, and the inference time is 37ms tested on the Raspberry Pi 4. Notably, we provide the fastest solution to the challenge. Codes and models will be released at <>.


page 6

page 8

page 11


Lightweight Monocular Depth Estimation via Token-Sharing Transformer

Depth estimation is an important task in various robotics systems and ap...

BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation

Monocular depth estimation is a fundamental task in computer vision and ...

CutDepth:Edge-aware Data Augmentation in Depth Estimation

It is difficult to collect data on a large scale in a monocular depth es...

Real-time Monocular Depth Estimation with Sparse Supervision on Mobile

Monocular (relative or metric) depth estimation is a critical task for v...

MobileDepth: Efficient Monocular Depth Prediction on Mobile Devices

Depth prediction is fundamental for many useful applications on computer...

UDepth: Fast Monocular Depth Estimation for Visually-guided Underwater Robots

In this paper, we present a fast monocular depth estimation method for e...

Data splitting improves statistical performance in overparametrized regimes

While large training datasets generally offer improvement in model perfo...

Please sign up or login with your details

Forgot password? Click here to reset