Adversarial View-Consistent Learning for Monocular Depth Estimation
This paper addresses the problem of Monocular Depth Estimation (MDE). Existing approaches on MDE usually model it as a pixel-level regression problem, ignoring the underlying geometry property. We empirically find this may result in sub-optimal solution: while the predicted depth map presents small loss value in one specific view, it may exhibit large loss if viewed in different directions. In this paper, inspired by multi-view stereo (MVS), we propose an Adversarial View-Consistent Learning (AVCL) framework to force the estimated depth map to be all reasonable viewed from multiple views. To this end, we first design a differentiable depth map warping operation, which is end-to-end trainable, and then propose a pose generator to generate novel views for a given image in an adversarial manner. Collaborating with the differentiable depth map warping operation, the pose generator encourages the depth estimation network to learn from hard views, hence produce view-consistent depth maps . We evaluate our method on NYU Depth V2 dataset and the experimental results show promising performance gain upon state-of-the-art MDE approaches.
Code (0)
등록된 구현이 없습니다.
Tasks
Depth EstimationMonocular Depth EstimationSimilar Papers 제목 키워드 기반
Align3R: Aligned Monocular Depth Estimation for Dynamic Videos
Recent developments in monocular depth estimation methods enable high-quality depth estimation of single-view images but fail to estimate consistent video depth across different frames. Recent works address this problem …
Depth EstimationMonocular Depth EstimationA high-precision self-supervised monocular visual odometry in foggy weather based on robust cycled generative adversarial networks and multi-task learning aided depth estimation
This paper proposes a high-precision self-supervised monocular VO, which is specifically designed for navigation in foggy weather. A cycled generative adversarial network is designed to obtain high-quality self-supervise…
Depth EstimationGenerative Adversarial NetworkMonocular Visual OdometryMulti-Task Learning+2NVS-MonoDepth: Improving Monocular Depth Prediction with Novel View Synthesis
Building upon the recent progress in novel view synthesis, we propose its application to improve monocular depth estimation. In particular, we propose a novel training method split in three main steps. First, the predict…
Depth EstimationDepth PredictionImage GenerationMonocular Depth Estimation+1Adversarial Patch Attacks on Monocular Depth Estimation Networks
Thanks to the excellent learning capability of deep convolutional neural networks (CNN), monocular depth estimation using CNNs has achieved great success in recent years. However, depth estimation from a monocular image …
Adversarial AttackDepth EstimationMonocular Depth EstimationPhysical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving
Deep learning-based monocular depth estimation (MDE), extensively applied in autonomous driving, is known to be vulnerable to adversarial attacks. Previous physical attacks against MDE models rely on 2D adversarial patch…
Adversarial AttackAutonomous DrivingDepth EstimationMonocular Depth Estimation