Single Image Depth Prediction with Wavelet Decomposition

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

arXiv commentCVPR 2021

References in corpus (15)

• Distilling the Knowledge in a Neural Network
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• MobileNetV2: Inverted Residuals and Linear Bottlenecks
• Empirical Evaluation of Rectified Activations in Convolutional Network
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
• Learning Efficient Convolutional Networks through Network Slimming
• High Quality Monocular Depth Estimation via Transfer Learning
• Deep Ordinal Regression Network for Monocular Depth Estimation
• Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers
• GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
• NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications
• Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding
• Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Camera