Single Image Depth Prediction with Wavelet Decomposition
This improves efficiency for depth prediction in computer vision applications, though it is incremental as it builds on existing encoder-decoder architectures.
The paper tackles monocular depth estimation by using wavelet decomposition to predict sparse coefficients, achieving high-fidelity depth maps with less than half the multiply-adds in the decoder compared to state-of-the-art models.
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