Single Image Depth Prediction with Wavelet Decomposition

TL;DR

This paper introduces a wavelet-based, fully differentiable encoder-decoder approach for monocular depth prediction that achieves high accuracy and efficiency by learning sparse wavelet coefficients without direct supervision.

Contribution

It presents a novel wavelet decomposition method integrated into depth prediction models, enabling self-supervised learning of wavelet coefficients without ground-truth depth.

Findings

Achieves comparable or better depth accuracy with less than half the computation.

Enables self-supervised learning of wavelet coefficients without ground-truth.

Improves efficiency of monocular depth estimation models.

Abstract

We present a novel method for predicting accurate depths from monocular images with high efficiency. This optimal efficiency is achieved by exploiting wavelet decomposition, which is integrated in a fully differentiable encoder-decoder architecture. We demonstrate that we can reconstruct high-fidelity depth maps by predicting sparse wavelet coefficients. In contrast with previous works, we show that wavelet coefficients can be learned without direct supervision on coefficients. Instead we supervise only the final depth image that is reconstructed through the inverse wavelet transform. We additionally show that wavelet coefficients can be learned in fully self-supervised scenarios, without access to ground-truth depth. Finally, we apply our method to different state-of-the-art monocular depth estimation models, in each case giving similar or better results compared to the original model, while requiring less than half the multiply-adds in the decoder network. Code at https://github.com/nianticlabs/wavelet-monodepth