CamLessMonoDepth: Monocular Depth Estimation with Unknown Camera Parameters

TL;DR

This paper introduces CamLessMonoDepth, a novel monocular depth estimation method that learns camera intrinsics implicitly from monocular sequences, achieving high-quality depth predictions without prior camera parameter knowledge.

Contribution

It presents a new approach for implicit camera intrinsics estimation in monocular depth prediction, outperforming existing methods on the KITTI benchmark.

Findings

Outperforms state-of-the-art on KITTI benchmark

Accurately predicts depth without prior camera parameters

Incorporates pixel-wise uncertainty estimation

Abstract

Perceiving 3D information is of paramount importance in many applications of computer vision. Recent advances in monocular depth estimation have shown that gaining such knowledge from a single camera input is possible by training deep neural networks to predict inverse depth and pose, without the necessity of ground truth data. The majority of such approaches, however, require camera parameters to be fed explicitly during training. As a result, image sequences from wild cannot be used during training. While there exist methods which also predict camera intrinsics, their performance is not on par with novel methods taking camera parameters as input. In this work, we propose a method for implicit estimation of pinhole camera intrinsics along with depth and pose, by learning from monocular image sequences alone. In addition, by utilizing efficient sub-pixel convolutions, we show that high fidelity depth estimates can be obtained. We also embed pixel-wise uncertainty estimation into the framework, to emphasize the possible applicability of this work in practical domain. Finally, we demonstrate the possibility of accurate prediction of depth information without prior knowledge of camera intrinsics, while outperforming the existing state-of-the-art approaches on KITTI benchmark.